From ba8fb2b33fee1239deb40d5534c65c597c03378b Mon Sep 17 00:00:00 2001 From: Usamah Zaheer Date: Mon, 14 Sep 2026 19:03:48 +0100 Subject: [PATCH] Add Swin2SR image upscaling Learning Path --- .../swin2sr-vgf/1-prepare-environment.md | 82 +++ .../swin2sr-vgf/2-export-model.md | 45 ++ .../swin2sr-vgf/3-run-model.md | 48 ++ .../swin2sr-vgf/4-inspect-result.md | 64 ++ .../swin2sr-vgf/_index.md | 74 +++ .../swin2sr-vgf/_next-steps.md | 8 + .../swin2sr-vgf/swin2sr-image-flow.excalidraw | 587 ++++++++++++++++++ .../swin2sr-vgf/swin2sr-image-flow.svg | 22 + .../swin2sr-vgf/swin2sr-result-comparison.png | Bin 0 -> 59964 bytes 9 files changed, 930 insertions(+) create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/1-prepare-environment.md create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/2-export-model.md create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/3-run-model.md create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/4-inspect-result.md create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_index.md create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_next-steps.md create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.excalidraw create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.svg create mode 100644 content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-result-comparison.png diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/1-prepare-environment.md b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/1-prepare-environment.md new file mode 100644 index 0000000000..67e757b0dc --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/1-prepare-environment.md @@ -0,0 +1,82 @@ +--- +title: Prepare your environment and image +description: Install the Swin2SR example and Arm ML SDK, then prepare a 64 × 64 input image and its high-resolution reference. +weight: 2 + +### FIXED, DO NOT MODIFY +layout: learningpathall +--- + +## What you'll build + +You will upscale a low-resolution image using Swin2SR, a pretrained image super-resolution model. It predicts finer detail as it doubles the image's width and height. + +You export the model with ExecuTorch, then run it through the Arm Vulkan Graph Format (VGF) backend. The result is a PNG image you can open and compare with a high-resolution reference. + +![Equal-size views compare a 64 by 64 low-resolution input with its 128 by 128 Swin2SR output. The input is enlarged for display only; labels show actual pixel dimensions. ExecuTorch and Arm VGF run the model on the host.#center](swin2sr-image-flow.svg "Images shown at the same display size to compare detail; labels show actual resolution") + +This workflow runs on your Linux host using the Arm ML SDK's Vulkan emulation layer. It introduces the model execution flow used by Arm neural graphics; it doesn't deploy an application to a phone or measure Mali GPU performance. + +## Install the example + +Use a 64-bit Linux system (AArch64 or x86_64) with a working Vulkan 1.3 GPU driver. The packaged ML SDK checks for the `shaderFloat64` feature, even though you export a floating-point 32-bit model. The setup script stops if your GPU doesn't support it. Apple Silicon with MoltenVK needs a separate source-built SDK, which isn't covered here. + +Have Python 3.12 with development headers and virtual environment support, Git, `curl`, `xz-utils`, a C++17 compiler, and [CMake 3.24–3.x](/install-guides/cmake/) available before continuing. On Ubuntu 24.04, the Python packages are `python3.12`, `python3.12-dev`, and `python3.12-venv`. + +From a directory without an existing `executorch` folder, clone upstream ExecuTorch and select the revision containing this example. Keep the checkout folder named `executorch`; the build requires this exact name: + +```bash +git clone https://github.com/pytorch/executorch.git +cd executorch +git checkout 32a86b69388b5a5208e367a96b0f5b7cb39df8e2 +``` + +Create a Python environment and install ExecuTorch and the example's dependencies: + +```bash +python3.12 -m venv .venv +source .venv/bin/activate +python -m pip install --upgrade pip +./install_executorch.sh --minimal +python -m pip install -r examples/arm/super_resolution_example_vgf/requirements.txt +``` + +Confirm that the installation succeeded before continuing: + +```bash +python -c "import executorch.exir; from executorch.extension.pybindings import portable_lib; print('ExecuTorch is ready')" +``` + +Install the Arm ML SDK dependencies and activate their paths: + +```bash +./examples/arm/setup.sh \ + --disable-ethos-u-deps \ + --disable-cortex-m-deps \ + --enable-mlsdk-deps +source examples/arm/arm-scratch/setup_path.sh +``` + +The setup script installs the Vulkan SDK and the tools that compile and execute VGF graphs. Keep this terminal open and run the remaining commands from the `executorch` directory. + +## Prepare the input image + +Create the example images from a screenshot included in ExecuTorch: + +```bash +python examples/arm/super_resolution_example_vgf/model_export/prepare_demo_assets.py \ + --output-dir swin2sr-work +``` + +The script creates a 128 × 128 crop and downsizes a copy to 64 × 64. You use these two files: + +| File in `swin2sr-work/runtime/` | What it is | +| --- | --- | +| `demo_lr_64.png` | Small image you give to the model | +| `demo_hr_128.png` | High-resolution reference: the original crop before downsampling | + +The helper also prepares calibration and evaluation folders. You don't need them for this floating-point walkthrough. + +## What you've accomplished and what's next + +You have the example, its tools, and a small input image with a high-resolution reference. Next, export Swin2SR as an ExecuTorch program. diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/2-export-model.md b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/2-export-model.md new file mode 100644 index 0000000000..6ea07ed64a --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/2-export-model.md @@ -0,0 +1,45 @@ +--- +title: Export Swin2SR for Arm VGF +description: Convert the pretrained Swin2SR ×2 model into a floating-point ExecuTorch program with Arm VGF. +weight: 3 + +### FIXED, DO NOT MODIFY +layout: learningpathall +--- + +## Export the pretrained model + +You don't need to train Swin2SR. The exporter downloads the pretrained ×2 checkpoint and converts it into an ExecuTorch `.pte` program. The pinned checkpoint revision keeps the model weights consistent between runs. + +Run the exporter from your ExecuTorch directory: + +```bash +python examples/arm/super_resolution_example_vgf/model_export/export_super_resolution.py \ + --model-name swin2sr \ + --checkpoint caidas/swin2SR-classical-sr-x2-64 \ + --checkpoint-revision cee1c923c6a37361c6e5650b65dcf4be821e5d52 \ + --input-height 64 \ + --input-width 64 \ + --quantization-mode none \ + --output-path swin2sr-work/swin2sr.pte +``` + +The first run downloads the model weights. `--quantization-mode none` keeps floating-point calculations, so you don't need calibration images. + +The `64` dimensions fix the input size for this export. The model produces a 128 × 128 image because the checkpoint upscales by two. + +## Keep the program and metadata together + +After export finishes, check the two files the runner needs: + +```bash +ls -lh swin2sr-work/swin2sr.pte swin2sr-work/swin2sr.json +``` + +`swin2sr.pte` contains the executable model, including its VGF graphs. `swin2sr.json` tells the image helper how to read the input and reconstruct the output. Keep both files in the same directory with the same base name. + +The exporter also saves `swin2sr_delegation.txt`. It records which operations run through VGF and which remain in ExecuTorch. You don't need to change this report to run the example. + +## What you've accomplished and what's next + +You have a floating-point Swin2SR program configured for one 64 × 64 RGB image. Next, build the host runner and use it to upscale your image. diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/3-run-model.md b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/3-run-model.md new file mode 100644 index 0000000000..407edeab5c --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/3-run-model.md @@ -0,0 +1,48 @@ +--- +title: Run Swin2SR on your image +description: Build the VGF host runner and use the exported Swin2SR program to save a 128 × 128 image. +weight: 4 + +### FIXED, DO NOT MODIFY +layout: learningpathall +--- + +## Build the host runner + +ExecuTorch's `executor_runner` loads your `.pte` program and executes it. Continue from the same terminal in your `executorch` directory. + +If you opened a new terminal, restore the environment first: + +```bash +source .venv/bin/activate +source examples/arm/arm-scratch/setup_path.sh +``` + +Use the repository's build script to enable VGF and the runtime libraries it needs: + +```bash +bash backends/arm/scripts/build_executor_runner_vkml.sh \ + --output=swin2sr-work/build +``` + +This builds a Release executable at `swin2sr-work/build/executor_runner`. You only need to build it once for this walkthrough. + +## Upscale the image + +Run the image helper with your exported program, the host runner, and the 64 × 64 input: + +```bash +python examples/arm/super_resolution_example_vgf/runtime/run_super_resolution.py \ + --model-path swin2sr-work/swin2sr.pte \ + --runner swin2sr-work/build/executor_runner \ + --input-image swin2sr-work/runtime/demo_lr_64.png \ + --output-image swin2sr-work/runtime/demo_sr_128.png +``` + +The helper converts the image into a tensor, runs the model, and saves the output tensor as a PNG. A successful run ends with `Saved super-resolved image to` followed by the full path to `demo_sr_128.png`. + +Your input must be exactly 64 × 64 pixels. If you see an `expected (1, 3, 64, 64)` error, check that you used `demo_lr_64.png`, not the larger reference image. + +## What you've accomplished and what's next + +You have executed the exported program and saved its 128 × 128 output. Next, open the result and compare it with the input and high-resolution reference. diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/4-inspect-result.md b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/4-inspect-result.md new file mode 100644 index 0000000000..fc14eacea2 --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/4-inspect-result.md @@ -0,0 +1,64 @@ +--- +title: Inspect the upscaled image +description: Verify the Swin2SR output size and compare the generated image with the low-resolution input and high-resolution reference. +weight: 5 + +### FIXED, DO NOT MODIFY +layout: learningpathall +--- + +## Check the image dimensions + +Confirm that the input is 64 × 64 and that the model created a 128 × 128 RGB image: + +```bash +python - <<'PY' +from PIL import Image + +for name in ("demo_lr_64.png", "demo_sr_128.png", "demo_hr_128.png"): + with Image.open(f"swin2sr-work/runtime/{name}") as image: + print(f"{name}: {image.width} x {image.height}, {image.mode}") +PY +``` + +The expected output is: + +```output +demo_lr_64.png: 64 x 64, RGB +demo_sr_128.png: 128 x 128, RGB +demo_hr_128.png: 128 x 128, RGB +``` + +Twice the width and twice the height give you four times as many pixels. + +## Compare the images + +Open `swin2sr-work/runtime/` in your image viewer. Compare the low-resolution input, the Swin2SR output, and the high-resolution reference. Enlarge the input to the same display size so you can compare the same text and edges. + +The high-resolution reference is the original 128 × 128 crop, before downsampling creates the 64 × 64 input. You keep it for comparison; the model receives only the low-resolution input. + +![Low-resolution input enlarged for display, an actual Swin2SR output from an earlier run, and the high-resolution reference at the same display size. Compare letter edges to see reconstructed detail and remaining differences.#center](swin2sr-result-comparison.png "Low-resolution input, Swin2SR output, and high-resolution reference at the same display size") + +The example output shown here comes from an earlier run with the same checkpoint and demo image. It illustrates the comparison; it isn't a new measurement on your host. + +Look at the edges of the letters. The output estimates detail that was lost when the original was reduced to 64 × 64. It won't reproduce every detail of the original, and a larger image doesn't automatically mean a more accurate one. + +Your end-to-end flow succeeds when the runner finishes, the generated image has the expected dimensions, and it shows the same scene without obvious corruption. This visual check doesn't establish a quality benchmark or a performance result. + +## Try another image + +Use another 64 × 64 RGB image with the same program. Replace `my-image.png` with its path and choose a new output name: + +```bash +python examples/arm/super_resolution_example_vgf/runtime/run_super_resolution.py \ + --model-path swin2sr-work/swin2sr.pte \ + --runner swin2sr-work/build/executor_runner \ + --input-image my-image.png \ + --output-image swin2sr-work/runtime/my-image-sr.png +``` + +For a different input size, export a matching program first. The helper doesn't resize or tile images automatically. + +## What you've accomplished + +You have prepared an image, exported a pretrained Swin2SR model, run it through Arm VGF with ExecuTorch, and inspected the upscaled output. You can now repeat the same flow with your own 64 × 64 images. diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_index.md b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_index.md new file mode 100644 index 0000000000..4ecddb8ee6 --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_index.md @@ -0,0 +1,74 @@ +--- +title: Upscale an image with Swin2SR and Arm VGF + +draft: true +cascade: + draft: true + +description: Export Swin2SR with ExecuTorch and run it through Arm VGF on your Linux host to upscale a low-resolution image and reconstruct finer detail. + +minutes_to_complete: 60 +lastmod: 2026-09-14 + +who_is_this_for: This is an introductory topic for machine learning and graphics developers who want to run image super-resolution with ExecuTorch and Arm VGF. + +learning_objectives: + - Prepare ExecuTorch, the Arm ML SDK for Vulkan, and a sample image + - Export a pretrained Swin2SR model as a VGF-backed ExecuTorch program + - Build the host runner and upscale a 64 × 64 image to 128 × 128 + - Check the output dimensions and compare the result with the high-resolution reference + +prerequisites: + - A 64-bit Linux host (AArch64 or x86_64) with a Vulkan 1.3 GPU and driver that support shaderFloat64, as required by the packaged ML SDK emulation layer + - Python 3.12 with development headers and venv support, Git, curl, xz-utils, CMake 3.24–3.x, and a C++17 compiler + - An internet connection to download ExecuTorch, model weights, and the Arm ML SDK dependencies + - Basic familiarity with Python and command-line tools + +author: Usamah Zaheer + +generate_summary_faq: true +rerun_summary: false +rerun_faqs: false + +### Tags +skilllevels: Introductory +subjects: ML +armips: + - Mali +tools_software_languages: + - ExecuTorch + - PyTorch + - Python + - Vulkan + - VGF +operatingsystems: + - Linux + +further_reading: + - resource: + title: Swin2SR VGF example source + link: https://github.com/pytorch/executorch/tree/32a86b69388b5a5208e367a96b0f5b7cb39df8e2/examples/arm/super_resolution_example_vgf + type: code + - resource: + title: Swin2SR pretrained model + link: https://huggingface.co/caidas/swin2SR-classical-sr-x2-64 + type: website + - resource: + title: Arm ML SDK for Vulkan + link: https://github.com/arm/ai-ml-sdk-for-vulkan + type: documentation + - resource: + title: Prepare models for neural graphics with Arm neural technology + link: /learning-paths/mobile-graphics-and-gaming/preparing-models-for-nt/ + type: learningpath + - resource: + title: Quantize neural upscaling models with ExecuTorch + link: /learning-paths/mobile-graphics-and-gaming/quantize-neural-upscaling-models/ + type: learningpath + +### FIXED, DO NOT MODIFY +# ================================================================================ +weight: 1 +layout: "learningpathall" +learning_path_main_page: "yes" +--- diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_next-steps.md b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_next-steps.md new file mode 100644 index 0000000000..e20dfa6d43 --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/_next-steps.md @@ -0,0 +1,8 @@ +--- +# ================================================================================ +# FIXED, DO NOT MODIFY THIS FILE +# ================================================================================ +weight: 21 +title: "Next Steps" +layout: "learningpathall" +--- diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.excalidraw b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.excalidraw new file mode 100644 index 0000000000..74c11c25c8 --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.excalidraw @@ -0,0 +1,587 @@ +{ + "type": "excalidraw", + "version": 2, + "source": "null", + "elements": [ + { + "id": "title", + "type": "text", + "x": 40, + "y": 18, + "width": 520.2421875, + "height": 41.4, + "angle": 0, + "strokeColor": "#17324d", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7321, + "version": 1, + "versionNonce": 9121, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495529, + "link": null, + "locked": false, + "text": "Upscale an image with Swin2SR", + "fontSize": 36, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 33, + "containerId": null, + "originalText": "Upscale an image with Swin2SR", + "lineHeight": 1.15 + }, + { + "id": "subtitle", + "type": "text", + "x": 40, + "y": 66, + "width": 546.1181640625, + "height": 28.749999999999996, + "angle": 0, + "strokeColor": "#495866", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7322, + "version": 1, + "versionNonce": 9122, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495529, + "link": null, + "locked": false, + "text": "Same display size; input enlarged for comparison", + "fontSize": 25, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 22, + "containerId": null, + "originalText": "Same display size; input enlarged for comparison", + "lineHeight": 1.15 + }, + { + "id": "input-card", + "type": "rectangle", + "x": 40, + "y": 115, + "width": 282, + "height": 342, + "angle": 0, + "strokeColor": "#c7d6df", + "backgroundColor": "#f5f8fa", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "seed": 7323, + "version": 1, + "versionNonce": 9123, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495529, + "link": null, + "locked": false + }, + { + "id": "output-card", + "type": "rectangle", + "x": 800, + "y": 115, + "width": 282, + "height": 342, + "angle": 0, + "strokeColor": "#b9d8c8", + "backgroundColor": "#f1f8f4", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "seed": 7324, + "version": 1, + "versionNonce": 9124, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495529, + "link": null, + "locked": false + }, + { + "id": "input-label", + "type": "text", + "x": 77, + "y": 139, + "width": 205.84326171875, + "height": 26.45, + "angle": 0, + "strokeColor": "#17324d", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7325, + "version": 1, + "versionNonce": 9125, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495529, + "link": null, + "locked": false, + "text": "Low-resolution input", + "fontSize": 23, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 21, + "containerId": null, + "originalText": "Low-resolution input", + "lineHeight": 1.15 + }, + { + "id": "output-label", + "type": "text", + "x": 829, + "y": 139, + "width": 226.30517578125, + "height": 26.45, + "angle": 0, + "strokeColor": "#246e4b", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7326, + "version": 1, + "versionNonce": 9126, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495529, + "link": null, + "locked": false, + "text": "Super-resolved output", + "fontSize": 23, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 21, + "containerId": null, + "originalText": "Super-resolved output", + "lineHeight": 1.15 + }, + { + "id": "input-dimensions", + "type": "text", + "x": 108, + "y": 405, + "width": 145.22705078125, + "height": 28.749999999999996, + "angle": 0, + "strokeColor": "#17324d", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7327, + "version": 1, + "versionNonce": 9127, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495529, + "link": null, + "locked": false, + "text": "64 × 64 RGB", + "fontSize": 25, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 22, + "containerId": null, + "originalText": "64 × 64 RGB", + "lineHeight": 1.15 + }, + { + "id": "output-dimensions", + "type": "text", + "x": 852, + "y": 405, + "width": 173.03466796875, + "height": 28.749999999999996, + "angle": 0, + "strokeColor": "#246e4b", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7328, + "version": 1, + "versionNonce": 9128, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "text": "128 × 128 RGB", + "fontSize": 25, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 22, + "containerId": null, + "originalText": "128 × 128 RGB", + "lineHeight": 1.15 + }, + { + "id": "model", + "type": "rectangle", + "x": 411, + "y": 196, + "width": 302, + "height": 178, + "angle": 0, + "strokeColor": "#007d99", + "backgroundColor": "#e8f5f8", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "seed": 7329, + "version": 1, + "versionNonce": 9129, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false + }, + { + "id": "model-name", + "type": "text", + "x": 462, + "y": 222, + "width": 182.51513671875, + "height": 37.949999999999996, + "angle": 0, + "strokeColor": "#007d99", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7330, + "version": 1, + "versionNonce": 9130, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "text": "Swin2SR ×2", + "fontSize": 33, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 29, + "containerId": null, + "originalText": "Swin2SR ×2", + "lineHeight": 1.15 + }, + { + "id": "model-runtime", + "type": "text", + "x": 445, + "y": 272, + "width": 242.20751953125, + "height": 26.45, + "angle": 0, + "strokeColor": "#17324d", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7331, + "version": 1, + "versionNonce": 9131, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "text": "ExecuTorch + Arm VGF", + "fontSize": 23, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 21, + "containerId": null, + "originalText": "ExecuTorch + Arm VGF", + "lineHeight": 1.15 + }, + { + "id": "model-location", + "type": "text", + "x": 469, + "y": 312, + "width": 173.892578125, + "height": 26.45, + "angle": 0, + "strokeColor": "#495866", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7332, + "version": 1, + "versionNonce": 9132, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "text": "Runs on the host", + "fontSize": 23, + "fontFamily": 2, + "textAlign": "left", + "verticalAlign": "top", + "baseline": 21, + "containerId": null, + "originalText": "Runs on the host", + "lineHeight": 1.15 + }, + { + "id": "input-arrow", + "type": "arrow", + "x": 338, + "y": 285, + "width": 57, + "height": 0, + "angle": 0, + "strokeColor": "#007d99", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 3, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7333, + "version": 1, + "versionNonce": 9133, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "points": [ + [ + 0.5, + 0 + ], + [ + 56.5, + 0 + ] + ], + "lastCommittedPoint": null, + "startBinding": null, + "endBinding": null, + "startArrowhead": null, + "endArrowhead": "triangle" + }, + { + "id": "output-arrow", + "type": "arrow", + "x": 729, + "y": 285, + "width": 55, + "height": 0, + "angle": 0, + "strokeColor": "#007d99", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 3, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7334, + "version": 1, + "versionNonce": 9134, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "points": [ + [ + 0.5, + 0 + ], + [ + 54.5, + 0 + ] + ], + "lastCommittedPoint": null, + "startBinding": null, + "endBinding": null, + "startArrowhead": null, + "endArrowhead": "triangle" + }, + { + "id": "input-image", + "type": "image", + "x": 85, + "y": 189, + "width": 192, + "height": 192, + "angle": 0, + "strokeColor": "transparent", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7335, + "version": 1, + "versionNonce": 9135, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "status": "saved", + "fileId": "swin2sr-input", + "scale": [ + 1, + 1 + ] + }, + { + "id": "output-image", + "type": "image", + "x": 845, + "y": 189, + "width": 192, + "height": 192, + "angle": 0, + "strokeColor": "transparent", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 0, + "opacity": 100, + "groupIds": [], + "frameId": null, + "roundness": null, + "seed": 7336, + "version": 1, + "versionNonce": 9136, + "isDeleted": false, + "boundElements": null, + "updated": 1789395495530, + "link": null, + "locked": false, + "status": "saved", + "fileId": "swin2sr-output", + "scale": [ + 1, + 1 + ] + } + ], + "appState": { + "viewBackgroundColor": "#ffffff" + }, + "files": { + "swin2sr-input": { + "id": "swin2sr-input", + "mimeType": "image/png", + "dataURL": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAEAAAABACAIAAAAlC+aJAAAMQGlDQ1BJQ0MgUHJvZmlsZQAAeJyVVwdYU8kWnltSIQQIICAl9CaISAkgJYQWQHoRbIQkQCgxBoKKHV1UcO0iAjZ0VUSxA2JH7CyKvS8WFJR1sWBX3qSArvvK9+b75s5//znznzPnzr1zBwD6CZ5EkoNqApArzpfGhgQwxySnMEldgAw0AR14A28eP0/Cjo6OALAMtH8v724ARN5edZRr/bP/vxYtgTCPDwASDXGaII+fC/EBAPAqvkSaDwBRzltMyZfIMaxARwoDhHihHGcocZUcpynxHoVNfCwH4hYAyOo8njQDAI3LkGcW8DOghkYvxM5igUgMAJ0JsW9u7iQBxKkQ20IbCcRyfVbaDzoZf9NMG9Tk8TIGsXIuikIOFOVJcnjT/s90/O+SmyMb8GENq3qmNDRWPmeYt1vZk8LlWB3iHnFaZBTE2hB/EAkU9hCj1ExZaILSHjXi53FgzoAexM4CXmA4xEYQB4tzIiNUfFq6KJgLMVwh6FRRPjceYn2IFwrzguJUNhulk2JVvtD6dCmHreLP8aQKv3JfD2TZCWyV/utMIVelj2kUZsYnQUyF2LJAlBgJsQbETnnZceEqm1GFmZzIARupLFYevyXEsUJxSIBSHytIlwbHquxLcvMG5ottzBRxI1V4X35mfKgyP1gLn6eIH84FuywUsxMGdIR5YyIG5iIQBgYp5451CcUJcSqdD5L8gFjlWJwqyYlW2ePmwpwQOW8OsWteQZxqLJ6YDxekUh9Pl+RHxyvjxAuzeGHRynjwZSACcEAgYAIZrGlgEsgCoraehh54p+wJBjwgBRlACBxVzMCIJEWPGF7jQCH4EyIhyBscF6DoFYICyH8dZJVXR5Cu6C1QjMgGTyHOBeEgB97LFKPEg94SwRPIiP7hnQcrH8abA6u8/9/zA+x3hg2ZCBUjG/DIpA9YEoOIgcRQYjDRDjfEfXFvPAJe/WF1wVm458A8vtsTnhLaCY8I1wkdhNsTRUXSn6IcDTqgfrAqF2k/5gK3hppueADuA9WhMq6HGwJH3BX6YeN+0LMbZDmquOVZYf6k/bcZ/PA0VHYUZwpKGULxp9j+PFLDXsNtUEWe6x/zo4w1bTDfnMGen/1zfsi+ALbhP1tiC7H92FnsJHYeO4I1ACZ2HGvEWrGjcjy4up4oVteAt1hFPNlQR/QPfwNPVp7JPOda527nL8q+fOFU+TcacCZJpklFGZn5TDbcEYRMrpjvNIzp4uziCoB8f1F+vt7EKPYNRK/1OzfvDwB8jvf39x/+zoUdB2CvB3z9D33nbFlw61AD4NwhvkxaoORw+YUAvxJ0+KYZABNgAWzhfFyAO9zH/EEQCANRIB4kgwkw+ky4zqVgCpgB5oJiUAqWgdWgAmwAm8F2sAvsAw3gCDgJzoCL4DK4Du7C1dMJXoBe8A58RhCEhNAQBmKAmCJWiAPigrAQXyQIiUBikWQkFclAxIgMmYHMQ0qRFUgFsgmpQfYih5CTyHmkHbmNPES6kdfIJxRD1VEd1Bi1RoejLJSNhqPx6Hg0A52MFqLz0SVoOVqN7kTr0ZPoRfQ62oG+QPswgKlhepgZ5oixMA4WhaVg6ZgUm4WVYGVYNVaHNcHnfBXrwHqwjzgRZ+BM3BGu4FA8Aefjk/FZ+GK8At+O1+Mt+FX8Id6LfyPQCEYEB4IXgUsYQ8ggTCEUE8oIWwkHCafhu9RJeEckEvWINkQP+C4mE7OI04mLieuIu4kniO3Ex8Q+EolkQHIg+ZCiSDxSPqmYtJa0k3ScdIXUSfpAViObkl3IweQUsphcRC4j7yAfI18hPyN/pmhSrChelCiKgDKNspSyhdJEuUTppHymalFtqD7UeGoWdS61nFpHPU29R32jpqZmruapFqMmUpujVq62R+2c2kO1j+ra6vbqHPVx6jL1Jerb1E+o31Z/Q6PRrGn+tBRaPm0JrYZ2ivaA9kGDoeGkwdUQaMzWqNSo17ii8ZJOoVvR2fQJ9EJ6GX0//RK9R5Oiaa3J0eRpztKs1DykeVOzT4uhNUIrSitXa7HWDq3zWl3aJG1r7SBtgfZ87c3ap7QfMzCGBYPD4DPmMbYwTjM6dYg6NjpcnSydUp1dOm06vbrauq66ibpTdSt1j+p26GF61npcvRy9pXr79G7ofRpiPIQ9RDhk0ZC6IVeGvNcfqu+vL9Qv0d+tf13/kwHTIMgg22C5QYPBfUPc0N4wxnCK4XrD04Y9Q3WGeg/lDy0Zum/oHSPUyN4o1mi60WajVqM+YxPjEGOJ8VrjU8Y9Jnom/iZZJqtMjpl0mzJMfU1FpqtMj5s+Z+oy2cwcZjmzhdlrZmQWaiYz22TWZvbZ3MY8wbzIfLf5fQuqBcsi3WKVRbNFr6Wp5WjLGZa1lnesKFYsq0yrNVZnrd5b21gnWS+wbrDustG34doU2tTa3LOl2frZTrattr1mR7Rj2WXbrbO7bI/au9ln2lfaX3JAHdwdRA7rHNqHEYZ5DhMPqx5201Hdke1Y4Fjr+NBJzynCqcipwenlcMvhKcOXDz87/Juzm3OO8xbnuyO0R4SNKBrRNOK1i70L36XS5dpI2sjgkbNHNo585ergKnRd73rLjeE22m2BW7PbV3cPd6l7nXu3h6VHqkeVx02WDiuatZh1zpPgGeA52/OI50cvd698r31ef3k7emd77/DuGmUzSjhqy6jHPuY+PJ9NPh2+TN9U342+HX5mfjy/ar9H/hb+Av+t/s/Yduws9k72ywDnAGnAwYD3HC/OTM6JQCwwJLAksC1IOyghqCLoQbB5cEZwbXBviFvI9JAToYTQ8NDloTe5xlw+t4bbG+YRNjOsJVw9PC68IvxRhH2ENKJpNDo6bPTK0fcirSLFkQ1RIIobtTLqfrRN9OTowzHEmOiYypinsSNiZ8SejWPETYzbEfcuPiB+afzdBNsEWUJzIj1xXGJN4vukwKQVSR1jho+ZOeZismGyKLkxhZSSmLI1pW9s0NjVYzvHuY0rHndjvM34qePPTzCckDPh6ET6RN7E/amE1KTUHalfeFG8al5fGjetKq2Xz+Gv4b8Q+AtWCbqFPsIVwmfpPukr0rsyfDJWZnRn+mWWZfaIOKIK0aus0KwNWe+zo7K3ZffnJOXsziXnpuYeEmuLs8Utk0wmTZ3ULnGQFEs6JntNXj25Vxou3ZqH5I3Pa8zXgT/yrTJb2S+yhwW+BZUFH6YkTtk/VWuqeGrrNPtpi6Y9Kwwu/G06Pp0/vXmG2Yy5Mx7OZM/cNAuZlTarebbF7PmzO+eEzNk+lzo3e+7vRc5FK4rezkua1zTfeP6c+Y9/CfmltlijWFp8c4H3gg0L8YWihW2LRi5au+hbiaDkQqlzaVnpl8X8xRd+HfFr+a/9S9KXtC11X7p+GXGZeNmN5X7Lt6/QWlG44vHK0SvrVzFXlax6u3ri6vNlrmUb1lDXyNZ0lEeUN661XLts7ZeKzIrrlQGVu6uMqhZVvV8nWHdlvf/6ug3GG0o3fNoo2nhrU8im+mrr6rLNxM0Fm59uSdxy9jfWbzVbDbeWbv26TbytY3vs9pYaj5qaHUY7ltaitbLa7p3jdl7eFbirsc6xbtNuvd2le8Ae2Z7ne1P33tgXvq95P2t/3QGrA1UHGQdL6pH6afW9DZkNHY3Jje2Hwg41N3k3HTzsdHjbEbMjlUd1jy49Rj02/1j/8cLjfSckJ3pOZpx83Dyx+e6pMaeutcS0tJ0OP33uTPCZU2fZZ4+f8zl35LzX+UMXWBcaLrpfrG91az34u9vvB9vc2+oveVxqvOx5ual9VPuxK35XTl4NvHrmGvfaxeuR19tvJNy4dXPczY5bgltdt3Nuv7pTcOfz3Tn3CPdK7mveL3tg9KD6D7s/dne4dxx9GPiw9VHco7uP+Y9fPMl78qVz/lPa07Jnps9quly6jnQHd19+PvZ55wvJi889xX9q/Vn10vblgb/8/2rtHdPb+Ur6qv/14jcGb7a9dX3b3Bfd9+Bd7rvP70s+GHzY/pH18eynpE/PPk/5QvpS/tXua9O38G/3+nP7+yU8KU/xK4DBiqanA/B6GwC0ZAAY8HxGHas8/ykKojyzKhD4T1h5RlQUdwDq4P97TA/8u7kJwJ4t8PgF9enjAIimARDvCdCRIwfrwFlNca6UFyI8B2yM+ZqWmwb+TVGeOX+I++cWyFVdwc/tvwAiJnyqLU7ruwAAFdFJREFUeJzlWglUFFe6rrW76Y1e2GRRNlnEuD5EjaMSRyUakjEJOIzRxBAxGiMZjONknjI6yYvRLJpjJEpUosboqDnRoIOJIThKMgqCIIsisjT70g0NvVdX1X2n6jZFs+jMvJf35vjePX36VN2623/v/b////570f4+G/KzJgAAiqLuzyiKAgB+3l4QBMEwTKfToT+7AP+bCcMwDHmUE8uyj7YACII88gIQyCObcBwHAAgrAPjf8GUZFT3cQeYhEDQs/x9/RQZy+H8UQQQQcxVDUYSmnUePfl5aWuK+hYSOWb4yi6KDY3UfFgCse+bA/0BllhUGxH/inodJhWGYUAbwMgsjhg8o6p7vwmL38hRF7d+///r168IWGuyAJEmWZVAUh9UoyokgAMdxDMMRBDB8giVxPsFnmnbytVCC4NpkWZYgCBRFnU4nw3DPBEEAAFiWoWmGZVlYl6ZpkiRRlCtP0zSOY3xHGMuyDMOwLNwXKI7jBMFtGAC4jqCEEEKH6AAvMVtWdsvb25um6Rs3/ubt7TtjxgyZTHbnzp2KigqlUjlr1iy5XM4wLEmS3d3dN28W6/X6cePGTZ06VS5XsCxz9+5dAICXl1dhYaFYLJ49e7ZarW5qaiopKcEwLC4uztvbG0FQk6m/uro6Kiqqvr6+trY2JiZm4sSJDoejrKysoaEhLCxs6tSpKMoBPYZhDQ0NpaUlNO2Mjp4wceJEDEMRFCAo6y4AhiDcnmFZ5J133tFoNBRF6XS6ltaWXy9PiYgYf/r0abPZ3NzcvHDhwg8++EAul5WUlGZmZur1eoVC0dXVNXPmzLff/pOPj19WVlZdXV1oaGhNTU1zc3NsbOzy5ctPnDih1+ubmpqioqI+/vjjsLCwxsbGtWvXPvnkk7W1te0d7WaTefPmzW1tbdeuFfb0GgyG7t9t/v3LL78MAPLFF19kZe0XiUUYhhp7+155JfXVda8O7tD+PpvwM5vsfUbrooVLpkz+tysFhe1t3UcOH/PS+j0Rv+j63262tXYePHDYx9v/u29/oBzsju3/sTbtteqqex3t+vzvr4wPj/788+NOik17Zf0Yv6CTX55pa+26kHspKDBk8qTpF3IvtbV2nT930dtrzJ6P9tFOcON6iZ9v4IrfvFhdda+xoSVtzXqFXP1G+pt193UN9c0vvPDi5MnTm5vaW5o7fpOy6v3de5p0ba2t7e+/vycwcFx5eYXB0PvYY5Pf3/3REDsAFYlm6MWLF8+Z87harVmydElgkP/CRQviZk7XaNULFy1QqZWNunoEQTZs2PDhhx8GBQURBDHxsZiw8BCdrhFBgZNxxEyMTnx6qUario+fFz0hMiw85IkFT2g0mieeeCImJkan0wGAQEV67rnnIiPHBwUFPPPMrwiSeOqpp8ZyKfDZZ5f19/f1GntVKtW+ffs2bNig9JRLpdLZs2ciCNLe3i74EO46ACBk4Rim1WppmmUYGkGARCLRaDROJ8spFctCACEI1GKxHMw+WFpSarNZcAKvrKycNWsWVF+VSoWiKE3TAACRSKRSqQALaMC9kiJSwB+CwD09VRQFVR+XSeVyuYKmGQ4ucALDUMBy1SsqKk6dOtnUrKP45HDY3WFXEIAHLwRFALcOELx4/OLyWZZ/RDCEtxsoipjNloyMjPt195OeT/Lz81UqPfX6HpYZaBdgKMB5POVq8ojMASKPQpzmDQA0GIB21z8AHAQDbhAoAChJktXV1evWrfMP8F+0cJFaozab+6qrq10CAAyAoSgEBCncQNqV5fpxOQRB3Lt3P//7/OzPsp9P+hWCID2G/t27d8OBDZSHmIbCAQ8CnesZto+64buA8a7iAHAw/eOPP9pstkPZh8YEeCMIcvlyPk3TbkZmUAChGZRluHlCUYzPxHg8hqaNSwzD0DSr1WpValVBQUFUVJTD4Th58mRt7X0c53YXwwAI4DDB1oT+WFeCpoMRPnF2gKEH5OeL8f36+/ubTKa/5P1lzpw5LS0tBz49YLfZualhUZqhOWuDjEj+/v5qtYZvmpvRwICxCoUSLgVBEMHjQmUy6dixge+8887HH3+cmpqqUqmWLFny/PPPSaUyAFA/Xz+LxTpgUNGAgACNRsNvS+4XEBCg1WoRBBGJRCEhIR4eHnBePDw8gscFkyISzr1UKg0JCQEAzJ07d9WqVXv27Dly5Ii/v//ChYt7eoxikQRF0aCgIE7ZRhKanp4eiUQik8mgJhgMBg8PKXwFAOj13XI5Bwgoira3t3d0dGi12qCgIKPRSBCEXC43Go0AIGq1ml9G1GjsRVHU01MlNE6SpFKpoGm6p6dHpVKTJDdoiqKMRqNGo4GGnKIcRmOfVqsRiUQURTU1NZlMpqCgILVa3d3d7enpKRKJ+IF5jCIA9PJg95ymYJw6wtVHUc6q8x+5CRbMPvwEi0GAc+2SgVcImu7V4TPD50P3BsO47SqwUNgyfMVxzq/h+2EwzNUCbHkUAYZ5lMLrgzxNQaXgEg3zVR9Sxb3iqK8PasG9l1EIzTCeKbw+nH+OdImHQswAuIwYAXiwaz3MCXXPF55HUeIHtfiPRBYePN9D6v4X4hToA1p+5CklhvyfFADHcZJLPwNj5psioCtCkuTPHsjBhCdhU+I41tXVmZv7TV5entPpHBUEHtKiQAuh3t+9e/e7775zOp12u/3KlYK2tjaBxP2zadhIYC/YsM8YhvX29r7xxhtvvvnm+fPnHQ7HSAEepE+uFvkktHbo0KHf/W5LV1dXf3//5s2bCwuvkeSgQyqkv4u2I9MQX0iABZGIrKqqun79+meffTZ//nzONeJdaDgmSFXhWGEOABxddjNVCMf3OEPGWXEA2BUrfvOLX8zx9fXV6/U2u41hGBR12UphrQSBh1kSmKBFc7d3gunEMMwlwIDdRYzGPp1Op1J5Bo0NtFotUqmMIAir1drZ2ckwrJeXl0qlomkaRTk+gCCoRCJuaWnBMMzPz08kIm02W0dHB4qifn5+fHCAnTBhQkTEeLFYDGXGMIymaYPBIJPJhEyGYUwmk1gshq6R++hZlu3r65PL5SRJsCxwOimLxapQKKDMFEUJK+BahKysrLNnT7e1t258PX3q1Gnbt//x5s2be/fuNRgMKIqKxZL169clJCRgOHZw76cGg0Hlqb569ZrFYklIWPTMr57OycmprKzs7++fM2fOW2/9wdfH5+DB45cvX87KyuKYEO9BWK3WjIzfzp8/PzX1Fd45x4uLi3bufPeDDz4MDw9HkMGIC4ZhJlP/W2/9PiEh4fnnkwAA+T9c/ujDj/74x+2PP/44AMjp0392xwSu9eTk5OXLf+3t7ZORkbF69Wq73Z6VlaXVanfu3Llr166oqMjMzMyOjg6SIFpbW7766qyHh8d777334osvHj58+LXX1oeFhe3e/X5qauqZM2d+yC/AcKS7u7uystIVieGZhkql9Pf3//rrry0WM4Zx2yA/P59l2bFjx/K+z+AKAACUSiVFUZcuXeK5DltYeLWo+MbVq1cxDKMoxw8//DAIlLBmZGR4dHSUVOoRGxvr7e1jNpt27NgRGBgol0sRBJHJZJcuXWpqagoJHcuybGRkZFpamkKhnDx58sW/5IrF5LpX1xMEER42/tTJP5eVla14YTm3U/GhvgnOUeHz58/X19dPmTKlv7//2rVry5Yt8/DwoCgKgCGRP7FYFBcXd+zYMejt1tc3rF27trS01Gw2m0ymO3fuuAvA6Z/TydI0AwDi5JNEIlGpVHl5ebW1tT09PR0dHVarlaIozk0FYOzYsSKRyOFwYBimVCp9fLxQFHU4KB4MxBRFDezPgUAdHyRkaCQmJiY0NLSwsHBG3LTi4uK2trZ58+bxmjpcgxmGmTt37qefftra2ophmNNJv/DCyn//w9a2trb+/n6bzTYoANSBgdpcQwRBtLe3bdq0SafTzZo1S6VSeXt7u6KCLtbnpnC84whZy5BPA6MXMlkWKBSKxYsXX758ee3atLy8vMjIyPDwcH6buaKUQm2GYcLCwsLDw6uqqmiaDgwIio6eMGbMmMrKSrPZHBwcPMLWuoU7SRK7evVqRUXF6dOnY2JiSBFaWnL7woULkHa7h03BIIV0o7+uAqMEbgEA8fHxhw4fKii4Ul5evnr1arFY7HTSJEk4ndQAoXUVlslkcXFxxcXFZrN5+vTpMqlk8pRJRcXX7XZ7bGzs6IadZTliwXF+gqBp2mg0WiyW+rqm7Oxsg8EA3QEYQXCNFUNZjmS4CC6MawhfBXIDeRJE0ujo6JgJMe9/sAtF0fj4eJblqF9BQYHVah1mqgEA06dPLygoqKqqmjlzJssi06dP++tf/3rt2rWZM2cOXwEudEOSnko1H5fl9l9sbGx6evqECROcTmdISEhERAQcolQqp51OIXoslyk8PKSCDCqVSiLxgNxXrdLAWKxarZZIJJBnSSSS5OXJL720cuPrv/X3HwMAmpeXt3///vPnz8nlcvd1YxgmJibGw0Pq5+cXGhpGUc6IiEilQkk56ejoCcMZGYqivb29ra2tkZGRBEHgON7T01NcXNzb2xsdHT1+/Pj6+vqAgAC1Wl1fX8+ybGhoKDSQdXV1BIGPGxcMp7yurk4sFoeEBDc3NxsMPVFRUQCwNTU1fn5+fHAXkUgkRUVFSUlJOTk5c+fOxXF88+bNra2tR44cgRM0dEewdXX3RSJxcHAw7O7+/VqWBeHh4cMFgK4BSZIOhwPm8KFtV8ScYRiCIGCEnQ+Lc9FzuFUgN3c6udi38EpRFPRAISKJRCQM0jgcjo6Ojl27dnV2dh47dkypVDIMs3LlyhkzZmzatAmCqfuQUBQViUQwBC+0D3sfvoWgwyOMHq6gcGYBrTfMh46q4L1w2OqGgIIkQpd8pivYWFJSun37dpZlMzMzPT1VDMOYzRabzR4XN9NNd4aMyr19AIDQ/t8/J34Il38QM3SvMrIMH2sxtrS0BgUF8kFYTkKapjs7O319fR/kbEOvSZjHQfz4lxx0Y1z4loupsAMABaNmMKzyCJxSDoYX3ZL7ZkP+v3PiRyhhAw+jHBKPyB9Z+H8qgQdrwnC+JuQPPLCjHX3D/OG79r+f0NHOoR9OkYfJNroS8wTNhVnQQR+JX0I37sfawiHAyDLDgr5CwrlThVGmnC/Pue3DqgzrZRQdgI40DITweIcNHM1DmzVkMtyCMVwA2Wq1WK0W/rwag2vIsgyCcIc6Dj4RBDF4PkdwB2EWi8Vms7pXgREkhmEsFjO0/cKCwGebzcaxYYKLjQ9fAQxD7Xb7iRNnz507xzDM7Nmz4+Pjjx8//sYb6Wq1ZseOHStXroyNjeXNMHbkyGGLxZKens47J/dzcnJu374NAJg0aVJaWtq4ceNYlt2zZ49SqVQoFF999ZXD4ZgzZ86aNWs0Gg2CIBUVt48ePXrnzh0Mw2JjY9esWePr68sdk9LMxYsXz549q9frNRrNs88+9/TTiTAGUVJyMycnp7FRRxD4ggULUlJSiGF2Dsfx7OzsTz75JCUlJTIysra2dufOnaWlpS+nrpbKPHJzv/nlL38JFxFFkaKiIpPJlJGR0dvbm56ejiBIUlKS0+k8ceJEUxPne0OPrbq6eunSpcuWLdPpdAcPHqRpOjMzs66ubsOGDb6+vikpKX19fUeOHOno6Ni7d69YLP7yy5PvvfdeQkLC4sWLq6qqtm3bqtd3v/ba+lu3yjZu3BgaGpqcnGQwGM6cOXP79u0hnBjHsY6OjuPHj69Zs2br1q28I8RmZm67UXSdj2KgIjHnmQl3PKDbBw/OUlJSFi5cGBwSiCDI+PHjU1NTW1tboe/t5eW1ZcsWf38/FOXcu+/zv9+0aROO42lpaYmJib5+3ImTQqHYtWuXwWCQSCTZ2dkrVqzYtm0biqIMw6jV6vLycqvVun//fi8vrwMHDqhUKgxDpk2bturFVYOBLbiPGxsbLBbTokWLGIZxOCixWLR06dIvT37hikLxzEu4WSIok1arXblyZWVlZXFxMUVRdXX3nbTTZrNB1/Cxxx7z8vKyWu0SiSQmJubq1asOhyMkJCQgIKCyspJ7pRw1NTXQBezq6urs7FyyZAkAACrhxo0bKYrq6+u/VngtNTXV09PTZrPhOD5p0qSI8RGDWwiSbopy4jgJQ04cN0VYsYR0c7AgFwPDxDYajdu3b79y5YrWSw3rAsCgGH8fA2VFYi64CxPXFMrpYnNLc2bm1pKSEi8vL6lUajabcYJDPpO5TywRyRVSGIlhGFYkEstkMp2u0Wq1KPnjRjgvIpFIqVQOIfUMywYEBLIsW1JSMmXKZC4GSGA//fSTyWTidQgHCOfHCmdbJpMJHrifOnXq4sWLBw8emDZ9qlQqLSoqWrFixagnI5BPYxh28suTZbduZ2dnR0ZFyqSyr899nbktk2EYrVbrcDi6OvWREdE8BOG8p22VyWSeShUM+8FZs9ms3d3dLkSDuTRNh4QEJyYm7t69++TJUxUVlUePHv3mm29IUsQyiFLhKfWQ3rp1C8pQU1NTXl4Ob/s0NjZKpdKYmIlarRfDMHl5eXD/jMRovjOOY3R1dfn7+0+aNEmj1lit1svfXYYB0+DgkKjIyJzPc2AgyGq17dix4+233/b0VD355JPffvttXV0dZEt5eVyEahRDlpGRQVHUvn37FAqFv7//qpUvvfvuuwzDKJWK5OTkQ4cOdXd3yeUKi8UikUgoimIYkJycnJ+f/+qrr06cGNPV1W2xWEhCzNAAARjtZBma5fced0zGsSonjWPYokWLcnNzX16dGhYW3tfXRzmcfEmgkCvT03+7ZcuWl156KSIisrGxsaGhYceOHSRJrlu37t69e2lpaVOnTjWZTEVFxWlpa0dSSo43Yhim1+vtdntwcHB5eXlSUtLp06dnzIjt7TVeuHDhxo0bWq02MTFRr9c7HI6EhAQcx8vKys6dO2c2m+fOnTtt2rRLly4lJib6+Pjk5uYq5Ir58fEMw+A4fu/evfLy8meeeZokyZ9++ikvL49l2Xnz5oWHh//444+JiYnwosjduzV5eXk6nc7Pz3fJkiWTJ0+Bo+rq6rxw4UJ1dbWHh8eCBQsef3zOEAF45WB27txpt9tff/11tVptNBp37dpVWFh4/vz5MWPGAAAvpLkub8BNAkkmXFYIsAzDiESkw0ExDCORSAAAPM11nfiSJGm3c9cFYBWX+jEMgeMOigsKcfaVt7i8deIWDXJRvjr3aeAyIE9rh60AQeD5+flbt25lWdbHx6erq0skEm3btm3x4sWwFcEReNCFxodcZRRg1/3SHzoa5xw4N3BxbjdfE+a7zt5Hp5QEgTc3NxcWFnZ2dvr4+MyePTskJIQPmA5eLxw5uL+X6bq+OPIrOrqnKJR3Hz13DQQWGXRjRz2pJ0kCx136zV9PGUn23MX4p0+HfsZEjMziL1txlyP/sRb+laNHEOQ/AcaIzC2TmsTGAAAAAElFTkSuQmCC", + "created": 1789344000000, + "lastRetrieved": 1789344000000 + }, + "swin2sr-output": { + "id": "swin2sr-output", + "mimeType": "image/png", + "dataURL": "data:image/png;base64,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", + "created": 1789344000000, + "lastRetrieved": 1789344000000 + } + } +} diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.svg b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.svg new file mode 100644 index 0000000000..5b36cacddc --- /dev/null +++ b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-image-flow.svg @@ -0,0 +1,22 @@ + +Swin2SR upscales a low-resolution 64 by 64 RGB image to a super-resolved 128 by 128 outputRead left to right. Swin2SR uses learned super-resolution to reconstruct higher-resolution detail from a low-resolution 64 by 64 RGB image. ExecuTorch and Arm VGF run the model on the host to produce a 128 by 128 RGB image. Both images are displayed at the same size to compare detail; the input is enlarged for display only. The labels show their actual pixel dimensions. The two arrows show this single sequence using actual example images. + + + + + + + Upscale an image with Swin2SRSame display size; input enlarged for comparisonLow-resolution inputSuper-resolved output64 × 64 RGB128 × 128 RGBSwin2SR ×2ExecuTorch + Arm VGFRuns on the host diff --git a/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-result-comparison.png b/content/learning-paths/mobile-graphics-and-gaming/swin2sr-vgf/swin2sr-result-comparison.png new file mode 100644 index 0000000000000000000000000000000000000000..6062e32e0672806bb7feba3551c0e756fd9c8489 GIT binary patch literal 59964 zcmc$_cT^MY+BX_NMMXeGMCpnMN>c%m4x)e{y>}Jqz1IMO6sgjsOP3mu9!gN8m(Ykc1>>c=o&Z_kQQBQ`fiFSu20wWV|zT&sBcqnlI|A3e;B_uYy1z>Nkq7G(jMW zcOVd1(PeVrNb4yHqVKFfP8&F5jjq4>Hr zv{LT+1=;h@HRjQa!R(jMKN9R$|Mk~F5cfX^*n24Q{`D0*ZN&dCC;jextGMs9v|xlb zZgjsJ1mlWvnlGqkuF1QHTrC}~x*If~>Q36+j$d#4?J(>0N?u+UVi-!&hj@h79v$fp zW~gL5(Z!uDac~NI9E{tzG4SKOx`z^r6WmSIc#VpDCrZJ-?y$T-P}wkmg@G$6g@{Ef>qE!Q&|q|R3I1=`5>y7~p?T*j!$)&_b8$`N^dL6NKd5R(@T z!)iT-gR>tkE$Zwh4&uxL6POa`zOi4;Qy&%0ir2l$5icV)MHk_u})TQuqS5JJiHXe5Vsuc~;-j zU1)mROOdC3|E{3pZ@ql^bq2fwS?+c0&Ne#R&*GJ>Z93wbfx$EcMp|@(L~{@MJq;X5 z@M8;nEX;>EfQX8Ushq9k6>6WrAPu3-bz zbAdi|Ht3}&WX=&INb(DHZ(CDgly;ultwF%s|9P$4X z1qUAtWgIP|wMbW;%jho1ex-aRdp+{vtQRWp%X?bs4RUtPM7NH z0OCG&sU^zux%vfw5m5yB`P*@2KvE8UtfQrOWX19z^ZHO-pVp&&hyX?9q`1Z zF9(XMG-^IEX_)h#SWW#E0Z-qnw9dDWWNWWZ0rEsCGm^EObB%Cc%%5SLgP2!ZpU-!qNqWsV64VJ?~ zAdD}p+bzTQf4`Koxi27%bYxW-!(mXb`Tn!q@-cFN`0lopw*Bh z)rxM~T?2x*5xxH&w5FCd_ubUwP%JSaQ6WIYc4lBYJeD~oF3Lf@0p$^L$<%E%h}>jj zrR#x65ow8H>33m2E9=SJ$Z|KvSJJ}}qVe*jpV^kCHl>AfeekE8? z;7&fpy#_y3Dc7%g&c($gA(5FAe|VdZd^q1IRZxn>HQU$b^mA|E@KI^qc4ga=Yx;bh z6}$o?-QtE}6}EC!>N}XQOM#dk9{(6Y1`=J$)&@^~*ZB3_F&uGLA1!ga3+cy9ZKtU4 zDKmdmJrhKFTk4T)cwAyehS$1W98uWq`M0RR`QM#~xB0VQtj4j)2N-_m;LH@>ovBTK zZudM0sE4O`xD<_WcG{UY>We~--;xGV`Np-bmlAJ0(X$G4!ex5m7_b1h8R^ACK1miC zcWv#^gVoh?o-YI6Br$DVVL(7Iaao~?DrTQMAfB&H?N6C{yk1!06`2Dg7daF*rQ>pX zL<5#qf;pABNWz400V(S0_{vpaGavSFt#$V6&Us@9XWXu%qho0Ay^#_@OJCHRR$pI~ z3>5=*5DQ-_eDa%KuhOKORQq9qF;bIvxT)EB^O^8vvd>{*G>p!7TVI(5AY%NlyT-Cg z2MqExIAOh-ajQUTVWdtz%3E4`d!G*5U5fGEZ=y8~JPw4@Gy|RGdhyt*t0ZZLDWl#| z{GUC8qf>e*bCDL?{TkAJ)Fsx9E_=fCJV}&K?B=Ce1X_0xYEnkc@6Df#1iyZAhidzQ zOEW_H?2ISqdU1_f9BRD{{p)L17I@`vbraQX$-R}a4y1p00JFCbY54jT5ni7Gv)YxR za5gQq@PMf^cw7B(@x$Vxd3Q9$*5+41KcaLF!`wKJ$it?m1U=U4ZmzDZ0c%ZjbH<=A z7X2+)7=s=>2mG!dM;%4NuI!4G>XeYnOdTs^`w&-39)N^PbvUJmCFJt-VB)=PPvb#e&MqcknrPipn=&YFQ}(IH4eooWQe@3=R}@ zwTS7GnH!0v0erYmY2HQ*Mw!w*R1*a@l$W*f@Fag$1a>x{b(E9Xb><8d0nTNHzQx04 zF!{zv-Jw&y!mcUIc729kI`HuIZo2R$1So(BewriKndk&jcqi^JN5AC4k))j{;uKBA zR4L(mhNIsug4S{%+b)&7=<+4=_gN3v{E3}id`4t*LLZ&6fBv{3y`)*eC!tr58Sw;& ze9a_Z^GVBMr5_go%P^=b^>lx_n>Ajm(%PFiF*QgTN{ajWkc(cU`nvDF zUB~gjCEfVJn!z+|>ocG9q6w(&A(olfujRX5DPXqd9e&dy6M|q?NMd=peN!(z_3_rY z>66{Ka8y%`w!Z`+AuYMiy|WJv!=mabSsll7``eiu(_XBqx&7R@e>4i;nOKBi0F%gfWa0k4%i`i9UxqN@ zB$1XaaG|X|igshxYV@0iWV6SYxHukqHe{J!15!RNGCCSmg>L^fP+lHfui*IB)f}fL z!LAwm6a;DAD{soyF}B~Kgut%K#pn%j6=Hr*9gYJ{{-nZ)OdsY#*UA*1UG0aK0uf>^ zhQKwSTDPwTNSBUykg^)a-mFb6q~-*SIt?*Sl#c%KXh0nA>`fIBCHqw|QvWIl>-3~6 zq-Kx8Nctq@HFx>2xwOdWjUPW4a(q9G{S1Z0upV!KG49s05AWX(Ca$pjUl$@Rd#dnM0ts6g{^#Of`U9XYR4d^&$Ontn?kKe@ zrUB{&#aFZ|pHWl#fV>c^kjnOKGZ$^{&&Jdi{B5<*Mm2`QH9ghu6BVXWvt{9{N>F!u zw7ZxI{}eQaX*1QX^3L93kAPaHL~?u@wnG3$-0O#cY^TbnYm8Er{Y*zoOpIV>j8-FD zoEv*3(mEx^C7PXA*Iti%4|%QjXO;XAc&ci(PO~fKWv#$rF_u!HtXG+ihyQ-vpRx^Y zbLpQfb8NIYN%~@O^QJY?jXBzC#aK0=rKQCx3?`qmce6j`E*>#;ygm8o4>(*UZ)a|9 zj-?sXg6Ul!vx1Wi=Q?bQkT7`(T%q?lP7MdFJ_0`gT3Y@v+hF5>{WA&ig2W>OoV;kX zXjGfszTMyWrx9sfCx|9zUi*~250_u6X;Mz1gI=YE^DU!j-qZ@DX?s&%INF7Wz3u1pw(SUpiKZIa@&) zIbGVrkK3f0d6{dv{>;?iWKc3OD0%t1Ih?gQ`U$8niQfU+Jhu75JmxyUBw{vUES=1M z{yH~FqSyv=_i2p)iU2%}OHTqvZh}1Qrb+?S9x*muZNdbKO5vyYnx0r)V?;!)<)<~V839{L9M<(!`LYDiG>=A9t z+M1)moc-K3p?xJcmfSDV1YNxbempAVFa=Fc@ln`y7RyRKX;~S~PThdEIdsSB*iAu9 z8v^EoUmrQ*7JDF$&5OP`XJ=3F2YGYkOu1Q2LV`fgB3&eHUwEza=1<2gu}kB8H*K}c zpgyxOg*Z0&;Gj-#`;f(xY+7O_5fjppJvcb%@q$@R8aJGeL6{fgGVyJc@?*7X$bg#e zlT1o~Jz;4YLkD7id|f{87QJ=l$q{#`Q&} zX@!FhUM8dM8EPh47Af-Yo)zh~AH#r}u`!dj5;=DF?zV_Skx@L9YlH`}WWi%Om_hs9 zGlubTMZ4%|Re+=+cE`tRvtvT2;(e>H2<_eTp07KU0R)5*XnJ}Ys5CE9rK*{+?sgI` z2L)INKxs>d^lz|9<(>`~n)}_!ZQJ5W<^+x=*@+1W34Lz;Xx9GA+Hy1}5P|tq1tjk2 zX`@*iVXGRCrhfNX3+Q%SP3X7lwVn=upq)UnN- z@p*HRO0x!xu9=m@bj6wX?BW42Ll3cwHz z+taC|&wfo+YUdi~nN2`yP;^mvEo0`OidirF**1zcwpU@W&GIl%HyeMv0tQp+A)FSUD==;y9I&LV>UlYhK9 zlJ%i{p0q;+8q5${yTS|g+ycE@Vhhw<8h&|JFj3|w^0>}tV=vy60)llNkMqN@_4LEl zq`|(sVKMNwXG`%`*~Oy0d6hOZtEnfKsz?jJ$mE>T#mv_LHgtG!0DyQA$7vkUNdt1k zVv@oxd2DB!=jgX63YV+pqq_W1InV7pZ4G^Kn`2a|{7k;xlFJWOie4FeCi@f*rY9yQ zx@FVk1TEd#c~e=WV$|S)5?|O%HA`!Lw-|5Uy}^q(K%WRG5dJoyLCGx3i+-pRqmEF< z=u7|};91#HQghho?~1OK#mnlxmBN5&!&0*Y5`tZS{`{HayC3M&*fCNh=Q8F36iD+-iAj3t$xvWS~{guGh#f zzmwz}z&`wzIP~K%-S5Ap4%IHHuQ22{YKlB~k28pXdThM_!pNO5S?%o+kBkq$b@~a` z&x!VqtDLT`r>5({o(NLob?u7=Q|ST#Pzn)xTD{b8hY%nanVvheZO3=>>EZuSV9GRH zCcz&p0rbabS|41==q0hC_4awSeVP%3?d6rvqJ5=j9dPr&Qy=?XM&Y%y{R|~4%0v@r zRr+IN?sO5G^Gs#+KCm&Fa&vQ2Ac+MWL6&zdS&4IFNtcUWT$3N7g`Fwgd}pbv3*mv# zJXxm>foK>E4}p<4j4RR`!eH*(1X?ovM)&EzUlJ=}C$^&dO4k8_1s!uI;INezia-If z-l>T)Uuflh`EyhTeZgm(C0>hPZHC;mcO^^W*Vzh>&(W-SBaN%pw(YwGe@&IlQ0h$S z0CcKA(x$>=xP_=Xx&_-MVj4ik3mN?ppYwMj2B@%ch(LkWui_Y~r!Yn8R?Dwg%ukD( zUH-zOt^}6Z`qd(Yi5~`4^$2Cqs6x+QF7wP{=bKoa?WJ$U{vVclFvuqKi4h;kH}_Kh z5*IRw84%NCTc2RIa&3Q72X1FAbE)6Q7Xq^prYO%bVGhSptRTvdc?>X@Eyk>qT z+25)ey`wuo@Ed5nBDg+;Y;)5yG&D^6{F!m0%w!sd7S_8K5f@i;7&@%1`RdiHSzW#b zqt@?^yN24tGNjLG!9<=-VxeF$LCoeLdfH9I36YYNaP#I;xpDP}@aGjytiC3P4`T>x z=$Yz{C0KC`fSb=kqda%!6SK2f>FIT_Vqo zVU(JXu3PQjr0jR%y-+#JlOg~Ebf&}mt2g^qPxqV8g+)SrgtFE0>I^2gi9yAy{$mHo6zQdOVH)|ML zD64Go=~)QR35Z>5s=8MVfOP@nx7uLK@muGj_F~JkcRev>la*A|SEd_mDhlkbv*&!f zc>Yb^IzA^L_xeIL9akC&3b6aWzWMI~l0IU${(S~4=;x2N7fXXlwY34QzPh|-{K!=? z_tTynLCXN#al_FR5B@m0?dE?@muc&tFmKmc$*;?Q({X9+VRUPd>|^p3x|)B4^Vjkb zW7rOcoXJuRgku;#%M9skH}$}sTjmxZ?p=^QRg2Ha5Dz$D8?zjmX*os~tgJ*tM7VzW zGRP>>f{P?;g?iCra{nW~|7Y3Y{~Y>XA= zv(klYe%5gO?kKdn;3IP$0-s6TX=&MzUb#!u_WBUkpy6Tl&D&&4vj6&y*AbyY_w?!0 zQKpwqtPj#CUekAGrex2T`qbFab(ON&2|FdGB_9K-uEgM zp4-hi@99ubQa8RG6KZ2MT*>uA`R|u-)uZQ*QN=j|W_4nsoOK_t2PWd4jhGXot%;Js zb+}hksgV7p?-))*AkMd->AeWzuzd$h0=@X3L`Wn7iN``Fzv+P;N06?>NsEXB^LI9Y$ zZ99bt0zG@?v7~Ye?i+_$In4YNe#FW7Pz-9iYY6tkwCslE0zlPPXA0>9ZwZYW%=j*t znbY;Fyka=RYtl>ZKHv?&?+S7eL_NAulHIX65s{Jh>cvC!1pK_jN9V=~$|Lf+s|Q~U z8moX@Mqr2Y0|zrJ0z{LOgq#+ae5e@IG7q|GIi#tns00P-{3o`UP*4F5!9=1P=~sxf z+P4>uqiA%Dx5b8VNP%AH&B6bnc1{QY!awlgnJQ<(?*52F2DApEO9E~ zt~U5wY-Mtsf$nB2*%E5683&+(z+bXVx`D1jBOLeYVh};9b398>y(y@!np9H;r z!C?Uj7X);;@<#C;h!*XSyM9T+LK%%Ai3B*dD6hIts`g zU@ZU>L;)Jkmsk|gb3e1Saq@xTZ3Ll9F90n9?05X_tbaop>K+N467yvf**q1E>=JgE zyW9?dSAY{W0FUz~7Esl~w~E%mSD)6|*o5O=EX>6y{fv9JIR6Mr=? z2>0MByVzsfzQ0cajNvr6HStnTuK&S0C`-_}Rg6YIgDFX3e@HhOls~ zXOsS0YKZOpNd|^{oj?rot-n65v+lYKYj~ELE-`4m4}ZH zA+V})?>^A47Lwj@J3N(7kU-5!>6!S2jU*-cuifyXvEw;fyBH`U;TYZ4m;CsW$NNX) zsv+DFFGm(I)I4`GRcBw%IkL#;4?jAn`B|vn9P~kl935TLIL8mKNtY83ZM%UEA zvHH2kq4%Y-9|9fM5RjWcj6RMC<~DY|&1dB3!(#~jpkwGO2D13=A(oW{CjNO71%D6F z=cW9ck@PW4(9O_cCAjYyqwY2LF_Bv{Z;O; zfhwd9tsg%~)p&SI&6ml1CE06U-1X?2PuLeNVu4k@IGb;6#FVF$uJs!)^V7hSK`(_^ z7Qs%aL-CV!Uk_WYAmx$T^Rn^b7nd2>4Q;Mgfvgo35fK3je4LFS&J@gI@d*Nm?QtN7 zxhg5d566~uqD_ruaZzD$j#Mk4t>k*m2|A9h^z>Xl>`QL4ohb)|EYZ=~m+>yU$$Cj@ zZ!b9S4KL0Ely-5w8mJ|MUQMc*62buoNkBX`+iX8S7uCJy{5!Bx=k2@mt0|&c_=g@t zdv1qN`KRT(Bl59v06CN&#(O}6TpZ8uQMEm z9Rld+Q@H2$v7A_~gVrBAaWYe~#CmUeSDYWr``eXd30&w4dhZeqU z`XeCiKgBGo3s?_J8|c|u`$ewaYXDpG;k4*~5RJ8cP?&+qH=nKlND9{&cMVq|D9LiW z19~r}-^GyGs{=48)D_cSIH0c+LASGYP<)Wha4%xopSu z0Rb2R&x*&w3@6IWMquce5QuOw zAE2ZGO43pvkr2Qr@_qv9@uP$A&{hBn+D$q=fwUNZn7$$%fLWttgCJ`k z0plA_tL+U9p+`;XAKkadT{`Dr-O(9O+)!t`;$DS?g~@Lee`vJMBopwaZk-@ERL7zF zIYy4;<4b>TAm%m$Nqh+ZCh2uJ>G0;!qkH#;`sjH)t;cX{xl<$SQ&e^TCQt&W0Amey+7+XP;0&_V699Z9sd9&9vG+WBkfnZe#N8y-^aWKw&Iu+}`Yb6U zbsgjP>eXpfob+6iNrqtM;+Rw5x1*_Rpw1PSt)*FxMe?7%gsx&U@Yt>=Wn&Sk<|EdR z116Of|DLF&Z@rO^nR78fvj)J>h`_y25u~I)P!{74zF3&~os>Z9Y!$g~m8o7|xs{+A zen#vp*#1M*(?1y;XO_%jx&P*uQ+Xb`@C0trDwY zQHBn*_mQRinvse@t(y%RG=3v_i*YQM=$SUOe5ZKfxwN9yVFnEQ@Mfv|i^+b~QWPUQ z_=1IXv$aQjy2j_M6VEK{_O+Av2)$N8>`*)~?eli~P$A0Hnx;_0DZhgp?TN6AW3 zgEaQ#iDDyn+B5LldVbf6L90Ety9sHb-)S??45nIfj{;(?4^f@|JX$RHOs~?2L=aex zW0fXb0Jdx6Z&5OCQg9!>>E0U~8QHS9^+~eX{c)nY*dtMkk%MIOhiBO-*}zB2_pG2B z-K-^+`@%h#z4)s;z+#CFcO;1-nloaxj@Ujywa=kp9>_Ml1Gan^G!=^t!xm2?s)8w2Av`OCNzZ@RN$|Pz#utZ-5dchnE5+E?u z+e^Ccya>`AOm8_na8oT#3=p7an=1C3^5ip`6WPJ$cdHc?6$%)&)?1~jK4}vg`I7;c zMwGkArB|x+@6Yh?+fCH=ny5+SZ{s5CwhQR^y}2&CUVXy_BqnL9XK2Wv(VjD?@$X+N zHlLvE!dul(M?(0w72t1;>d{rk9gV$#m8P(fMdy~&Q@Qk_EEB={-M`qKhz7x$p96t? za5x(g60vo9-l#Yb~Q1bd^(XInUV#F^TK zDRAB0o#|GM#4R2O45u{vsn%`EOFE9ix!*%i#NqG4&P)}0A=k>(Pn=H@{C7`e9*cAX zy5(6xAhrUN3NdK-Fo>fy^J@yoGUWUa_c)5Lfkl!{ps&&-Jy{3PfX*#aNd=F$56d#a(X7#FXmr_q=$V3uNSr z1eXWPm-EU4?KSFiwl}tBcsHA_Mypgbwok9NX?m@a`~AdG76Lr2jCk zZo%zCc?4)(#K>BXCh;&Lu^Z5wfg%J%Sh|?okhuUbozn!m#^T<2@vZ`AE!~B?3eRFc zGRxlj^YT6X6U7#RqWz4sAMm;x%;EE6chfBBlo}l8-Fw=}bRO%}8lU7t+Qi*gtlzpH z0mWp+Ig^m@lN?De6#zb^6M%UhoqhrKL;7U23=KQ@08|b)j`{g23#OoFh03j@E#-+a zZT?3<1-KyL3ug(ncrxq(?u$-yM{oWus>8K<#%wvY>>V+&1!gCtpG<6+wJ{Q?%pO0x zzmzNPv^!pZ{C~LQd%}DyGQhBxsp-5Rqz&8G%vPb_EG5b*EFgeBugq3MO}p{MMFZa~ zOr3{?tQ#L{=JVtBFQ{j}-j8VO; zS2(j?*5(jjpc(*smi*3eu~ph=;c3oHy*+U)3JyT}-3CQqG^Y$M@m|$K_v3#LP#+oI z3jjnpAMhCtN%Far+J8Kvhg8WCWNV{Wk~-Zo0;OU$eclw)gpS^n+B;!+p(t-6rLH{3 zdWAelnv_jgZu|mztXJ-g8JxmrMLK~GItd-7Pu98mdwcJm^f7((ZUpk-mDj)X0T@Ga zdmzq5DdVcNRhkq7$o(S5U<-I<7EhA$KwqC>gUvSW^243^X0~=KB;jv~gIy%nxycv; z-g{$dsaw~V%-VK1`O^L^aDPORooaD5KSPTYpOZy=2yc|01V-^RPSA6d%`6UkQO5r5 zK!jD!QkWNrL+Z?)xKs#I>g+^3Kble9ok`-S&jB1(|3N5Qw~9o-!FXn9l-r@J8F;NX zk4=HI^}hw2+dW=h?ULb~wx?$)+m$7n)h{E)?lRGh)yd5Y%=@&ug!qD<)%>&^GLvzO zWfXtEeUb&_qktq9*l_QA&)2jy4|vc4e-3Hdh$B`2tKn<%dvIpe3x@|{4j~)CrcmuO zN=Tbxk$z{`pwVWqY5m*Zdg#`tRir||lz*8y1h|d@+lb{1+WAt`x~oB<{kr@H)zFP@ zjW_5EvgZ}%uEIf(x9Sgx9lc|;R)emJ+n|EZBUi#&1!&T7?ySGy5eU_~8U{@5-TI&m z0A}n)6l6!-`?5?0;{+hIQ!SkKYQ?oZ$qe9iIlnMKx;pzC1yRkAq?G~mAgRD@;lq-; zchgtX8}VJamT)^@2xJ*EFFRJl!2cNMqMau$`xU4gid{EW=nh5mu2oQPPu6ATzDJ0q z7i~hblM=|^odBk-{4o}jFHH)lUA@08;+K~QF4qY03YUhoGyuuq)Ouv!oH9tZvbsKwJy13L?ZQz`_#vMWB1`&cl$%db~IfQPhL zr$(EMKwpoQ)U1I{7pK1L8rFUPQ1b3IScnkhg26UA>7TjU_x6X?#2$ zfq>IZD!JJ;Cvi1tcQgC9(e5wbY+jI6y|;NGA~+&S@sJm7+$Npoea|f?i56hO1|e48+@c28ba6RfQ~_u}ziL!+W`U5)X*;#v8fc2r zE1&UOXy1$;_|X$ln*6xV32{(L1TTFsFQija{};--WhIo2G5)WYCH`&e{IB(2{>761 zS2#KUrz>6lzoJ+FdGEtYLGgVBw@Sh1igh5jl0CTNPfRkLg4;vYA6^6cHUr>maLgp|DP2WCvt zIL_9t!oH`zvLs3->| zDz-uQIXKANVFmf_BNxMOJrZ{qD2GtyCnmd3Jo!e<1wTO4a>Jev|LyJR0e$`Y6|_)4 z>losF{oL#WY@owqO+9_J<|XX)J+>1L`R>oaWnZ`@lX;AlrltW^?=L=!jZ7XJ+EKdJ zrR80X^Rj`R&bz2oZ%9ToH8p{LcXUh;B4+65nD_x1;GZ{QK>PoY+Q!Rg5m5QD^gmzn z8`sFH#Q8r-Mi^VPd^?K(a_mW7*zSkg!N<#3j>nI$hQ%sg&Ffzc{`WNjq0fDpyYhxZ zF#E#Xa(d{^Y=-L$HfPUdXYRe_@1UwHF0gjp{VKkE?>|4OaegfXZaDME+{H+U_%C7+P@%qL8{r9r0|FtduHpyf*g0$b={;z)lE3j(} z1P4X6-Y#apy#CpW`3-Xo`+xbAz~cX6^W>mL50;=y5YHbrdEHb%0{&yT%3j|y)4hI7 zZaK6LFGsQO@XR0E87?;JpZf0jTZYz|w6TVFXlxMc-E7uF4WEBIJ|&{63??1ME)k;F z@8w7e2&k!$j>hf?BMRQo2_x!^6mDt!Eso}xJsxHZp014Mz#|C?kzl4H_8~chrnrRX z&Yhs~q+6is>T1wq-BRyQ^6KAD*4LZKK8J>qIX52?eA`!D$(+SlKy!{Fpavt1+v72G z?JbkV66sAdoSmX#gkgpcD~@N-Mk)tu62hi+h%2F%7e}Nlb4p9I$yi(ez-1X)cwJ(Y zT+rTL!4Hx8X5}1;>ZY?ygt#j1Nl45=IBPGpG1O)QW78fj1KT1Prd#2u9Wg1FrT-nEG{^ax|gVZ*LBM~rW=Tl9fyu3Wnc%=!`e}t0j zw0Z0c(pk?`xr1W4zu%eApKN8!nx%d>@a-w6h=An^;x}m~^FF~^k^SjbU?`hZc=f7% zxKhz!>FV8YdFDUBs?vO4$6tseVr#i;P($?3#C5WHj4ZPfW_oqFZRz!@y!&ma3tC4+ z=-lunliEG@E~hI5yGeyzZMhm%`NOfvK`1-AY-7V(xY*#$>UIIRpjEIT^JJ); zJS<$H;dQRDs?via+d|G$ZZH5%7E)GQ5iTAuIj5%PYPqhu9>`nb-K^VKv|HVA?#$ zP8Wx8s6+&hUO9P{V}~zjzmN{pnATB#8lB(L!YnQDeUV{6FIKLSLX?@|5BFuVT1h&U%Z3|Da`DQL-Q$NwW2nPfv!G zm-E6zn>3Y`M_@v6{cGjRZElr4Ybz_KK1d(6^thy4gKQt(u}pu0XX~$Zvj#_&pinA? z-|A|++4ujGVeG80WZMIK`$K=b3vH!)bqbZ(kr{obAHGqN; z{#zP?^$l7=t4<7pR|kbRG<5iGk52zIybdnRA&8cf$yn=igSZ}X8t!}4xfV0Nj@HzE z6qmAE`3%J?WEb8Rncp!gZs++s?O5@UA+DV<8T&0gj$N;KU{?f>9WbgM6W`6N*sT?5 ztABSE_3Got2hmPaEm?B{Jrl230|$jwSuumN3rsOIu!_CI&q9j0RLJ1YQ%;t2Kbb+7 zIU(M`8%w{Kwf;w3tZ+wM^m|%h<-B|)-Rhld_J~nRMurvEbTFrxg{F8_VlHao>Tl|f zDVtckkk?Wb5*dVpdL;9RWkC4y;kT^&^7xAN^|3b8bq2fQe%EGCeE;&yY4x(ebAQP; z7iXFb^N$2#UmR7d$3@-JQ?W$ws=CcJ=y5B|InekgocrVQc#DD(&y`xlpQaUd!Tz zqm@)u1cd|}Z13s)?uoZqPZZ418}wy`{XX=MTw`5`m1#@bcak!i6d(H0;KMJ+fquvD zmMS)F+DMRSw)A>fk(14Bt%~X|!1}1UA|D{|{@}=TvDD~%NOkKl`ANmY|FoR*E*DgD zP`C+VPU`Nz?$$Cd6G znSM=)uq-QZn4T)+w9nOWb56WfvDjBWna7RKYM~1zb1BRX)deJs-Xrn$0Zp+NM z^i08%1F(?- z*^Fgr_1XFG;R7$he@@ML>CYA6R@(_BVerAq8)1`HUk_o#PYdOGqP{YTZBAGd^(7Grw!X((6Dg+9ligXP6VX5;6*V=jF{65WjWKFQ zA@#9lFSPEMxaW@gSPYX$m=57X_TiTU(HnjzI~rpxKOdmwY8bjD2B&H)2W^!h?>oX` zcxNqNNWV>66cUNdU%o!sCPECm$|Cba@YP^iO3GEhfTERWf$!}po|tYAep6JUT~%>k zZ3cZ@T`95H^zy|}(^4I7X*fz=md?@h>FXb)_?nj7>u++;cJRjHqOB2Bt)Ry7F6=Ew z6h6hrMexv`DOW0`r!Wu^y=DGM=jS zVmvQ9ekYl}B;h98-<1ert@FHX8>4)xy!G|D%XpW}OhS4F`!9XX&Zc3Ps;o^9pJLAy z-XlKE%SC{m2?|bV7JMFotvRIW$hjd*4<J!mJ$6YO5;I`No; zLv9d0tF~SIwBL>L06O9Bkb9VDc=>k7+uZ_D9~Fjxito!W`HGLn#F`wtg@=-oZXHui z5Z4Z!DWzfkV^5bjvJ9;!{L+yc3)60rdY9I$I13Xe;T)?R93EOn!LYuvj=~|a^pmrG zZTWvN-#Mr|&qRV4D;x_|#ZnRdDU4Vf%4k9R*>bV{`~(EAVEeI?{* zoW!l**%jK6tddX)ZnHLtAPP!avQsOfG>Ay>;t8s%at5hnJf|2gF{cD2muX*GII{L& z3>qKTzJt6!S!qJGF#Ic|lwWb8ROdbS{y1#`$b~vg;Uk-b_x1L37&43i)092}mE=&^`JZIs;rd*!)>#i{}*h)laocW}k=2qXOaFqDg>ON35LzS(n^ z{A*@r`7K^C64P`0%gbdnF}#(~_@dW*xt>F5f(o1dVB8UzdX1%uN6IKSkk8+2X^~zy zVn?#}D5FgQ#GvL<`(j7<#JmP=gU#3_86cm}YDFq@6G|Jr(54<0`Ol5P#}lBNH*bz> zQPJR1+?Eu3q-s zVdlq47Q0E}%vi0BmPf%4O6yyGNr>ykW^1qK1%It*-}pDD;BLE`*YQ)T+$mcEeH3wn zV_c|}vR#|j3)u#?#VzE9*!pgK-JWm*`CEYmck~_nrVJW-C zBB~#HzTUINt>*;R+jC(ay0R^Hvjtw`A+fcV-N4NILDEr3m~^>+xPk;D1t?P$bAqjU z-!U!}7--lyyj}5DNvg0&E$hHnGKck~JiTo>R-Cs6MK~H$E0=EdNbKdbJYgt$P+Yp% zjDl*ZAiYRntAYF?`Vz0c_gYp44drc5meB?vDeMLq)arYzadi$UXazb&;n5S=H)-(i zq9DK_p=h*SU<{ye(HLg;>)PsV$?&IWo^@@N2^R}w!8)v*J`NgQwo(Xfbf zgQ<#`^NLkD$xa;G#8 ziY9pQ262Sb;&trU>2pARY*F&)FpL4Z95*7^x+DclLQ7l)`U7zR~w>O*U0_ zh`JniVYpF)1Jp3*$`d37_U+j7!OPqIR--)}xA+tw+kJ!gkSd{1+3PbPLp-kY?n`s)z-cN&^UsnqL?}F7-0X^0*F5)jrHti`- zMqzj3o+}FJW}2EegPxjqf%L21eVVySNFGvS$CXys#Xk_YU*189UGC5Pr1@y!3-6RHT}1=A}bLQ97OtPDOVPxW{Q4gr794a z(C@ZN@wd*8D+n%yXKoJ;JtX_n*-2qN-BRdEme8@&GtvR-IunwA6nMNfrLlFZq^Hhy z^1?7whY4f=uvgFBnUeVhtHEsQ_RVV-)tgmWfLDn7$ep+6?{wAH3W1Pd40X^*em6)_ zN$etfwXx3~R$iR1jBjsSs~_3UTpd+ATOg5aVIw{tla%z}32Yv|h7 z_%cBLr@tscO36w=`xj-*U2yyjH1CMgB#<{ItAWgZu9ggVgIy?SZ7`kUhi*lwraWL$ zUjh~&k?Ys{H*Hm~tUM^}lz%P%xbsGlk|^tIn7;3IA9@qbD)|`3iyhPQNc|o^C1lYC z&sBoB$Ch?s*YU;(Mf)}cRyi~PoI3b?!a%==zQ zaIw39YtsnBJ=YqIOV?cQvx>Q2ZV#ho0u5w}YL(~;UG359<_HwNt-`i+ZC{IMZExzg zTesz31ko&rP3-I8$V%lkAP15jYink0Fxv6MVWp>F9={YN0Mh=UE^9*l!(okal9gWi z*;V;4YE7b|@Xiz@XY_RQs{Afj;9@x2|3=$ewnf#q?Zaz8KtVtR1ZhP=T43l>q`Ny5 z>28J`MMAo}8-@_cp*EiLbO|d#N&EgEIjKI{BmgKe`vi2*^ETLzpREYKmX>@|4*dIB?y?) zXx{i-xR7Qv@C8Bae&%u{| zSWSJU5m>+1ay53`ba6C#9L_tt?xSl?5Fo_xlAnL^fV~CN-cGcFAtsHD0|wbhkEfZy zc)Ryy-(zoAb>tW&D|Edto^XMIjEtq=cmOMW=xM@rCVEB_bLW44I%CgLcQV|=Ub3;* za;K<(PsaUFlYi#+!n`Ggo&-m}MczEv{T6)u5gXp+pHVbcS4_mp?gc;8AE*l^dM_-N zZXuG%z;0kc3ODJDL{Ad5FW-zsl#@Nol7IIcKqC189=q8GiwOG`%C-hD9WCC8IFhBuqpbyK=i5gEkWy_VMcY3ZIO;4fEE8S`#ElaZ zKQC)iU{0ubFo;xR00u(s@cfSy(Q&Bj^G=At&GLlP^XW^LYQYJ18YS{*iGHiWLxW-$h&W z#}@?#^Bhg`jiX!Mg|tsrwgQt)FdX=VWK#iA+*V)|t<}S@b#*e5yshi~Wqg2MA?4xX ze)KQEtUm=K%No4HLET6rqt&D{0`2^As{#V%M=-_ubZa29J`=)#r_nT)*v4=^uwL#B zSQd`NZ(iJ9Q3KjYE97u?*iP4?4VJ09oT5qv`6-t*dod7;`G&|vI>?`ir zs(ZdyJG{VLqdS(voa@AE;rIx=Ro*11b%MYz8EfyOKHf1En)U-!s(m2AnSw6OMkk>k zc}3b~UVMKluTt?JA;Z-2$K1NScC%R#f9Bj5%9=(q!ote+$JRiPtyZVY)FBy@Kc<1Q5{udBr*%)PtMpHfclAi{;~9C} z@&m40W9W;Ay}5|Jr+MbeX21EJ%^;xKN(1j_KqSd=f*=wwaq+**iD0L{N_ld8iU5qe?TZY0{Pw1iB_bJ z4!2fQ6mt!)8^xd)|-{rJe z3gK(-6`WVDA>78@Nk1p#l{?-KFG-i>`E^B0hR|BhH(7D{kmSsM%}Z8!COpq{SUz+i zt}4yh1W;Bl^)11%Q92RYD%CS&N>}fhG+lQg^h2>=4rttBg zI7gFv-s>1D$t%TVY-wRSVb>#6A4gM+3wtNO{jW$6yf{+Cm47k_)~^Uy2(BNV=fHI`+GEFop zC=k6E-FmU*Y{?FtYZ15h*t$dM^dH?~?UigaU%6G)8srqL&!H6v{JH*?F+pNCJgVnk z@0Omjk8+&FK?tN{C;GWGC#R^5U6QF^?vV%meI}$*{~P++jyQ}U8uFr zR>*$an&_mYz+6vel ztH8=KDa4k%mRmV zFyQd;2c+710Z*(<7pl|zypNs12rTRYs%>Y;+Io{m#sqyjK};C;IyTEiE%K;qsZ6zx zxfpz|qlw8nal*q!p3Bnb)($xg^bBb2DusM3=(U1cPkcOCXf9WXv3{LXr2`7-W&;`d z5xni0^l>uECEpA2ExRRZ3`>gU^(t*%!($5-e>!LmWvKpk|A=$~GCU3+oitXAOO#ag ztADbG5;dSjRWY$bH8#v8$ELk2V!9DM7G!KqUyJlm0;|N~GWp~}9^V^k2l;YBmR`KT zgZed|+5*)!V-z4V-Bz2p+f8)ActVC!e}1ywu-P?0LYSYxq#=L@M-76qU>ca#HQZyj z^oaYAI4HR3EPU9j8Ub}ts2uCUDRb?oIJIEaq`MCibzN4pncRyNy16< z^;cA3bHPIK%_uo{O79rL(svqr4g$h&3>r2b#c*0O)4XRRV=*owR_HhJ>Ys*bxHw1R z$E7<1c86BbeNoBg*G#2Ro7+xn#f?w<_73$|a{zApA$8kyNk$FlC9U?HAp(j2s(HWt z86T3+k!gv#teVKlvlM;=!rkrcA5?dY{{23v3`DCC$Wp%2!j&jPITI%fc4hr^xQ%X9 znQ#I4k^D^L)Iy3hG4pA_yPTKFlIxm#Q+X!Q<&rxSLMcUhub;&!MYq;C^QO-1sNTi6 zNeD1LTF;XbNW&A|3ArVsB+RWPCf+T3V5<%p(lCc5nBp-E?|Yo`B^HN-6n}Zxzwuj0oZ%+^ zP$xz(c48?!GE!@eK?Cc6(OLe@%c23x^kXem#^RtZL?<)-2<#tP7!p6SK*lS#Mul9u zDz9wtnWfHfhcwqw{okakD6MFE(+EKt%bPr>1Nrb{;-2N1(C`2i+yI18p8N2;V_6F7 zEX+Nzry_!^PlgpFVQ@BPX!$u|ILOrGJxXNe&lcp+!D>yU<<=;E#-2(FZ$avoy_79f$lOf?b;l_uQ z4M|GT6|v^YYZniX4$ptsX`)ZtCVNGSrUrdagB@=xd7qqUS$X0jhSK8We;)4ek8!W+ zy(}8ec|K1Svc|b~!8L1gyR#zlqNQ|+5Do4<=Q%a_UAbpr2Z7^p#w^l8bhK5^GSj;j z84>bf&$iO0RX<@3uzZCg>-KIvZ#kMxR=#rU zcl>6`q>l7F?aMA=HjQX1(Z_gna?F9BJboR-d35P9Ti(!mG^XvZ)sVL?)XgY)fFx>9 zPRIcH>colbF`!htQkHeg?3R_P4#A}mH^00QzHr2|=XS+UDcmB^x1^Ox!_ECz%*7=x zJXF`*m9k0TC*WbsnNGst zm_cM4)hru7n+$O%t(8RiTxtsS16B=HGrVF>gEJ@?rRb3}v1&~k>C!(}H`$ShE)5x} z&!+*I{G*6}AFlU_S_p<4_2t8trEFDPzq5%rt1wY26dU2QOZ#55?tJ3c%P1GN8w=kz zRaC!TgxWw6&=nT_7MtgAqs|*_!lZdb*2I z6W*fkFc;U-WzkTK7g=6u3Jsl}$Hc;;c(6b7`w_=W;j^6u1b4eor1&UC+s;b^uE%2P z>aUKz2}~vXi|Mck6~=2m#(D-y7(?5Z(Bj>RjvW6ioWXE;usFSOv?d=Lx8M48yr zi1)(}VZH2;U7$ih!m9f~-0yHy|ASGubRBIgWkpP{6zLiTFkW2$J9amq^$X6+{ zU`3wL8m`$RQ^_+y0r2cYs>i1?Z4FMu^p=kJ9*wwJDp`geYdPsU`$RK$|EpBBwdd1p z^27w0@rT+u&1;uQnePcV^rcc~rnh!hnSY$Syhy^K&R`S*+6a||vI~moA#cv7e_A!X z3plhAU}G~>$Q0Tr(~;ksHQ(epwJQ{4U9fPSvz=nNcE8o^yoyztX%5}@9kdzE;yPbK zyX~LZ7~#nz{8DFh6naHlYcqw0NEwZ1(o!8sJVmN2B$}OYC}t|w=tq`eskl$B9R9{| zRJfop@*o!Bb)JSfEjwOi@5V!*BLovkRF?0Bt?8G)x1LJU%9-5013v+&WY_VS_E4bd zbowE%#apUozXUd>Vk+0jY5cExw0%os*2uuO-9=sG7Jhxl zHVZp-r2{a;g^`KRWq04l%8iEt+&~aMCFXt?12uZm@s&LQ7LWjO%vw}pJz(vVdXY9n z?7hd=5WNb0wClshT_6I zXt{jjb*_T&S_V3NgrK{GDVFK^Ki=|=8Fz7I{<+}8Kilr~uMPxeWz zXhZYv=K8jgYx5%Ibuh`~Uw$keFLw>*TUIZr6|Q{o2b*aPj?Uo2dmTTJ0EKR_fNEa$ zVeL>FSb>4DKLn0MNqmkk!y076$#~EP8(gj9U1RzyW#gGSY&o&oK!SI#&W!4Aw`*_x zV`qT5*1wnG{RDVzK7@Wq3oz0(i3G_pRtmS$LU0t!MH}?)M&EO@^a5~x=}U%ms$F3wZx!UOR@`_^hjIOh^lf-;pDG1) zL_)4F*3^O48y*#;LK>6KVZsfECZ+a-Z#?jgw986e?7D9E=<3fx4d$<*G}@6 zm_S`!to53|KD&ec;1aND8iE_8S}Hmpm)mzd_8Z_nQ$9TLKz+R%S}B7f99>YcXQM(- zVTLlp?)Nkx3c1md3Os(!`9SRE^5g?!@F)XSIL9aiQ~>jVj>ycS@eY%mi)%A?vnABR zzn_!Xo6`1D9YxF|78~A3v#qtE{(7p6UzS&H6%!8q+x%9STlOuQBNKQn-A?H;g~OxA zf_qISQ@3j1hRu?%ZE4r+>do~v^Ud?=9DOr(i+?^Z zmAD{)yUPBcts^`YQmRuWXJL zN^9`?Ch=I@O_K+nFPDHOEtrm-Wzxt77bm~!OATpe$q zFW%EEOMEL(bqlHt(P`ZClvYyATwZ(O!*Z2dwlTUcmmceJJ5I zHjFeYi}7TN=3^n@^n>gl#J*Xes`-jiQj|R%PjeOcpl%T!{19ug+g+zTQ`h%=@CA6= zma1Bx)(2DIiQ>QX+bcX*3qn22@rE9CyfKdvAGtPZ^YQ$KpurQBfD~LuH|*|lp!Z63 zUXtn+v83=$2|m9d8X1F)mthLRoeLafK)@QKDU2@TBe51$#^s_hfzgIzIL)(Pf2FL9ASl#j05Jib%vhAYoD?3tZ!$@%gPPucoLe~oRNQc0~PYUbtue2 zsX2CvGN7N~90~+tKrDTxBx)t3nRTrJ95&kR(V#kQLu3vD*;+>l*F@X?rH9a7 zqm8E0tD4<0{BEtHtde);rsimqO{QFM!cHYXnlZL*de6sR#Oa(7PVGmEVZ7X-uqiAO zXXTxG%>Qe%;39AbbN$^MyHbgn)^ob7m`nqzKtS+3ia2QpN71c&*Hn2ztggf`PnkHkQNqKWmOR0@oyr{fxL{AdTvZiGh$ zE-mU`P;S<*+xWps-Bn;u{9CClOE4pUsUbUyo2t|^6R(tEthj|-qXU_puBPS3Ndt7d zJX~oGiU~(bYMw8UL4O|Ytl9~x!4V|rDo8j}1DivS#7^!iDlcmyiDNLx2jX^vzL zLLz zhbEsJAz#Yr<%z5~53}dXC2C$N##gv+PeN$XU)DsGn~c8O^b7GkT`A;-F$zOHD6$RL z@)a^n{vF@`|SMMV<&dQ?*U;kFWP$`Y8_k@DnC?}k1;$1VYW8Frw z!TrdR)6u#=Y8NZhbwSqd=a6=vZ<3?6uUhyG4evmCEErQ_eROg&X zLHPOkdXhn5OS$r#Q{QOpabHM84=6MPO()}e_u?ydmRVnluW*yyoB#k)Cr>YVtoY#wVUy_1r)MhCD)VHqbgsj zc*AO}q{yT=q;LS;lnWhepp7^F6{3b;5q2hz5p zo4tk_Y2QvAm09WODIJ+2*J6HgO^?jr6Fh$olk{WAER;MUvl58Y+W+c016qq&>Ut&? z%Jg`lK0T~;MV3x8Pe5_Jd6j>>P{|0I9v7EW@axx0maF7zVU&ph%V1Ny?a|TUO|`gl z2g`!vifbZDmDm8JNfrvp9tg_a6VzC3kT42<)nZMTvHX_&>$vJbP}QLbT;ACz z%+wsos7f>?TzO6b4Snd+$H@%V?15IcF+=6Pk4_F`2e%EGOsKA`4TmC;!m^|77$GBC zE$0j2^ex!zl|{eHAB4?_riTy7EqhS^14HYXIyW~)IOuOeC*^aX2`gc8Uh5B7de36i z($s($=F2JLwgw|zJRoQmef^R&D|;Ue?+>aCq=ma6|(|EB>?O`}{vJfndz z*rbDV@6gh)UqQvtNJ>C}hpvHW7Ng$@;Ivry=tWv}B3|rLK%t_(z7Tx8Oc&y?x`t*k z`8|60u~14{4{nxt&?#W(cY_Ovf+ag`Al3l#UKIk;3JQ=X&xtXzK&9aRoo#4a@mwo1aHzohUSmRf)wyQLGw1 zDZ}}47g{I#+{$NqdOOoK07z-0i3MO21Mgui2_6V^t#b88ZRq$SS?Wc}T;^!f3Nn!I zUT2Cm@!b|jfeAO0L@Zu2n`(_MjJS07=MzzolWJ!L3G6fQZ>*8`1^+f@;{s?g|a-jpgk(8dP-8~L^1|GYtt zXB*&zJA6Cr`RB@_TtmEpa_nsZRaUUcG+VKMU_*tTrcSPDSEtNQ9{h92eu$OmzvlG* z&~;^Pr1S8|4;)kBIKQ;TJ-uTd`_--^#iOFkKYxn2*m??;GC-!`Lh$8To8v@#G_BO= zF=)m6u)4JD3-v^Bc~M`~o(p-CY}|CP-8EL){8-)7|Mjq7U}GmJI5adsBmJX@U$JUF zYhpk#*=HCvQfpZMY($$Uh&8qQlKbiN)T4&>%{dO%N? zu6p~f!EY!&WNkCo&r-Ont7}v7eQso}qU@{m7su>npHYRdBH?Ny7y7}J;?)jfB{g^6 z2J>W-&0?$~r9a8Cv|rB1)0a>-!TQKN&7oG8z*tpMDk_wgUVyH&IXx@rU(T7vsbYw{ z5-HBym@T-F@yQbu8OU2l&~92$42>5HSG$jL&4za)xJHogmGG+Ft63YmRaQ7DLwkGW z$Gk>$TYPWdP@$&TYJJkntV{fkur%!qCAUJ7N+Z^&9$IoMUJIc#hxNZZR*lGXDAl# zNRrGHM(?eLXIYPfbZ~~IG`XGGVNTpuzDV+&a+@Za$MJE8>W!7i6rGdrcALVfX;B56 ze1ThXXCz9l=M!xw)q?_R=@*8}dg0<&PsmABN_VB2zF@SfI__oJj|<;5kOWQ)Zny`$ zT8%{5d57B7^$hHoM|k4tJ5I9QWu|*}T9-TcWtVUHx>omTB=wCcd(ge2Qs}itJ7`Ur z+5Yz6te7umuMl;}A8zE*Q)G2?(cv{*S5RvQ>mbuGyfzuLG+O_YGNZ)GOC4ZbB5@Rk z-9#3S)PhAwUeXEB>;LzCTN2HpIW+fk{u-yjs(u@`CuEYY-*|FvH?dnx@r89==|%X__UW9RZ{x{KGs9H#uZ`M}2)7R3TD@_7oUu((B+CGGqwn{v zwe_U$;Dy(_87+at&D?Bm2xk}~U)~<1@Vzl9C!nZrD6=~hRQ*(L=6pL@Hl;=IX2R;M zf-(0kP6Hb5#AWH#&f}9l=m-N~@i{_nA7cW&ZgzCAt(l}(1?QGx1opC|B=|X18lg|wNjaFP8 z8cQ&qV4_o#RB;mY((7a=aBaJOunZFMd^O^K(E;n0cHY_hs4If;eH5{+u3i3kNaRoe zX+}cdC!n*e-Jk<~TnbHLX2Ck53_Fd!;@mlYS4Cx3$eH5G$sAeW zD%hu2c{Oi3k8K}`)Y@s$Nxq8RtAGhNjq^-|!TOTg6xBrfgmcXli2kMW>+6Ms-F$!i zqkF19ZlrCPz|~Hk5l*ijcctpl-8seX)pC`c)tO%pE4&q4X8c~b)5;Uk=A_ZhC*apf zw?B_Df^ahw6YLwX+xpyGh$?%a+0%P*C8l&V7wMOdJ&(hY1Hk-{j(jW*!{jTz&# zFR1ChpVW>x40dgNrh*C+rM1&Fzh`|jOya2%>(Bo;Hzo!e7iqHiiuENz{AAxQxNpH* zB=x=fhqyc#F^EF2qPGlDLgb%os0A_pZ0F!?lW?<}p0O`rSDg1c_f1RerEn2pMlAA3 zeMmhKs^TOI8}4APc`#1Da~y5oKhm@#uv6hS&a zec~TMFT&n=X7kbkM<62P5Uj~zDpB z_S&u|Gwu9$rUYPw6Szi-1+QjAm?9Bq-JT$fz@S{_H z`nvyO=DvpjELr*Yd;h;?o#SlYg*Y##DHfi|jQ`9uZ9d5byH!>hQ!ZsqZej}ypnX?f z($YmKZb*Hr=^ZyYbL=mV466)dcb|YgEB{iW@cZ>&`rJ_trB&{31``mAW20j&-m6A> zY^>{s-n!0SreL;^;Qte|1%Dvm$gX@V!I$scW20%Hv@?=gZG>5?{L?MJeO04->wATu zfB+r4E$`|h?=yUFBAP882O|_{L>)c;>5nz)lE`LYyvnX$V-=kOy0#-y%Jq?)rA^=J zi-@2*r30}zu6Ah#v{;1rMHR_eHYRv< zxmp*Jn-9IWP!|_1saI3pB9kY6Z>6~RG+Ho^YC&SqE~8DW_8&@xe-Ees2nj)8zYy@< za+w}Tt+RnRtS`O=_`zSKTWf`p<#*Q;cc}8$l|6DpwN732!p-=s?7dzWa zr;DT%-MjU4ZvY@^fjq~4(R>|9+SD$WVV=UR@HNU${?g~4!M)tsnZLg z#u$bobIdYgw~F=S9~%bz6`-~!wnVgEAL79MvGBnutB3%8dvgV0G-%*{?3!@t&=K|= zP)y^4Wcl7;0$?=9yf{9ESYckb%Ie_=FKzE@=_8G`QRDH%c+?%FW!AYAf-f=rLUkDxvy3cLu*!^AYN%((aYOYhRj*M>1E zZ!5blK%baL$NbEgZm)& zVK_|Bsef78d@Ih;h0Q!7eIN{M?Z^Ga%4`4Cz}rjtJgq_Xf4W>uM@hZ6m)MSExCt zlR!pGGzi7E#>>WT1nvhi(0_L?H(<6AYw1I>lrrZx3F!8tInN3W?2}wOk9LS_)fjiK zgIyGA)x7&WIYfW_PqXxWg#P}({i0@?lzShj+MYz>w1G(#JaDVa81OO21j20(&Z9L} z8W5N5Sqw3K{aK0R0VSNIji^1=G3xHVJ_y*ahVUKe@BR{UMIWwt#Af?Gz#Ls#PVNXn z^r4(mMcXTnq)K`v=1V#n$vHFDM!<2r+12R|M_kE#vllwp7>_mh{ew8^^b4)!UNT}< za=wT$3aQ?;73;;6%qarWu%Ll$sg-V1%lxj%u+z`>_aLQ}g*w+1YwmSW@>9tp9sXigl?z@ju9PZ0!dV zR%6FMOnXL;c^ABM3)qn>Pvyefwu?BFQk!u;JKs*hZnsZETPrbqouQpthh*LR-@Jy) zPVnbuZb4J%TLt%>%|0LP7H`=91SHer(@m#%=BbWm%oi;Mjf%_6*@A8KFnpIEB{4I5 z;4>PHvzc+6yN}=yyeUBk{kl-l>&Xj-{wV;vh7Cyof7VYF&iTz0yp#fq9Y2-o;BYD@ zZRvQ5Az4UU6O|O6DpZwP=ggG9J*&CK$getFHL&A_KVwZnuitHW0i5nFU}eFMo&lQ^ z6$r^3hGAuQbO)pXU;!7PP+WzxoO?CdO&wMV?gnHG9kOh$rM&AJSZrq@6CPIduk1lc z?KZe>jYG6+tl}?k8n(*O_d&(#XK)u(ouW`ceEZtm45Pm^D)}l1wZasQ>_f4@^<%3- zQ+Xn3%W*IZLpC;VC8j@s!~#TUzwHKypb{?0NdlEoY+3~4#9Lt)q4SS1GF;va^i!3# zYXSK?)l4jr#4pG~l5u{^!s+P~rjthlS(b^=5pUE35v%{tA-dSA@`8`lR2n@i8Z&DP zP|N_M8O&USVym+85PiR2xIl>}qJWzNY{AUb3HUK_UH$GGV$AmA&6l&o=Z>?tR%wxV z=Cp1@SMDHZ0};Brb}osL{q%_lz90NhBRp^`F2nZc)`MY+X`T1mx-J>0ijJW-&=?*o z$V4v5N1wOSjU z+A>x1-a9G#cPNtU;9v($tc$GGDsPZ*GG0aYb{~2|x)2}c*^Cle*$-Rjg0NI73=Ps= z^X8>X#qJ5N)-&Yf=HgT&wnhE@F7G5y=MLmm;xeqo4#tHYAr*2CT14(jy!u6Bzm)4nY3 z{iJ`}HP2c&Gs-n4Kb>T!8!7X4$ulyt7CRn&*l=x-WiFOXP2RE?EVBg&z}W6hgH(`l z2pX$NdDPpjH|>JtTjrZ7W@Qx@j1;A!lo{x`I!plpTf&FySq%nzQ|Gci{n)kc4RxB~ zZko{)A>ST12`bsxD# zHFInQcnh0VP)$(wP0t`Lg50cfrZ(&ny*STsJWTb3LBF>_VrvN-}ixxg5doeNcJ1)Nl_hbwTV}*xCVksBMKd&)hlN_3H z(*z}CFxo?^^XSoZ=P=kO@m@kA<~^zmiFRj$ULBbi9A!pLNRHF?NbLqa)~uMTkA;DO zL`>F-38?ESvl@FZB>`~={Q4l9qEX`$N zPoK(OZQN)^PYA$!OId*8V#|_+zkip3uK{13J`>!gfGE*(+7cLg^KH#FFDahi*#Ntw zO#TimRY#MSl~rA1?UOOmk~Yl~#>EMTAFO`zynM&uBgMf&KSS^9vMk4rHX=$X7zwom0!OK}yX zqN5Z7A+y$2;e3HL$=x(a=s9PIq~k4zKC?}12|Rcs-TWJ>ei;zqDsNMN56)r0)8<1ZLEA69j?C-zjK!uuu6W5-1*xueHmv}2Te zLbSo<00s5lMXrsxTsW;Z*1-~iH4ExnqsNr)^Qxbg|KJJSb>4Dno^*}d>cwZ;to2g@V9<#bFztQ? z{ORw;9L$wc0>lILv1nMhK`S?dA{EwmhozUK&t=ZG=XxmG$iU`x4geG)A)t$g8PrCQ zL}DP*9QO`oY$(v(Uhh0%2!Q#N=#n_Gp@;*=1E4@L9ozWlKLNhErLwC`0N6+HI7@5K z5GYYEFFho&n{Rs57Pc`0DV_OlxDk8-y8yZq6dnxLDv*P@yb}!N3SV?!=>vhUjVzhpcKm~D1naK?uZ9~|6zlDEe?AzlbdNXuPaA4P*1^%=}8g&7`Tx9La`I5@~p zdb+`09=$6kS_-yux4GxGphsmS6ikmG%-JhMV_fk19C_?s4G&Y0!B;@fRm&yH8UWW@ zsx}LI>>C5w8Kud$GOuMYuAMij0kgg|3>p>|iZ)mO3iQD$EhSgOjXd>Av5T;g4ZxS; zgciPLMB!%GNw857_}4UD$?o89JJ1mho&dDV++mDnZMeo~8R>wbuVwwPt90n*co{kT zg?J!H-+Fr-@1^lO11#F##a>&1rmX^r5<@WS1dNvHk^D!T;kKLAe*I}wSM~d!lNK*f zuc~O_p#V!U)22Pae75>kBCB5c?)yBRXt&97aOK&(RR~@(#)L>vhOU5BFldwYj=2ql z(QFc|c`0wS3}JL|unz(f92|ze=yYLSsU&idCxCBhWQSaRMp}N^=9+0KJj!Hs2PU(P zN9_s>Jy)WoM*l$7$At3#4A(tuP>aIyX%AW5%#aiKdop2!zxbnv?FbPlzs7%N=QNPx z`2Kpv-s8>D=tLxY>or;%2rb8aR=^Ch$!6njVr7haTdTPu7RSkerIjA&w2p#Q18g163ujYgth;RD+B4xcaS1bOu~+=wcgeQ!MTxmHmt zXhq7|PvPFDX5Q<6J^)6(2N-Zrs-zSf1~<+Qy?Mh_2Q=HpmPe&EJ-t^M0qq|a1aK*8 zFCwv-+MVl05URNK&{<8n(@YP zJ1}mqjgw2&``I7M*!#^ScpJbO6Od6ZDSdi85bXvR0=Vne1jJ)wH4(yHv>1 zMg#9F2*}%pOge#C?;cj5dN}{O`qNw*Ukniuc+|?vbAu_p2sALIhj$-=Mq8h0Z9Nn{ z$h9o(5cPDK7d-;xlMe;qOz|Z}Aw+nEgkmj%cly?a-ya@C4L-S-%(1>3{}cuBm=FXE zt=R!3T8Q27G*ek6Gf7N1s7C=wqJ9~}frL+=f?@t~4A6-1-nJc=60YV9@OhsHphCP@B5tN&z4Nfo8f^!{_6+-2vBT>P1o9zt0lPrCtJMAQ&j7Mz268K0PoW& zbD%&ev%Fe-lW^B}rpg>Yj2#$_0cm-l{%W@oa=bYv_gX$s30w`L=@v+qeGDydj12^C zuaA@fFvxS%GbyG^W2xSgz>4wxuFVj@7e0Oh4=0~MKi~fqId-dR?{H&tugTx*T=$7~ zz!0`dJjRqLr!@llj-$cWhso$Kq)oL7ic*JfhgCs=19K28L?Okt2z|yn3X^6N-lX0o z%WDQFR5p0A-%WPJKRE17i)(~X<}criKba(oM+@RvF33dZZ-8mKfBt0sGp5;aI{YS` z-}_H%4&L=s+h`y`!5u(XC!)Wy+A%z^I(KDSVhzuzk+)A5fohc ztpH|5={PQS{$RWlIvG_ z_r%f6_`^F-nq6StpORe=^!Ry6fjx3nQyX^v$Lnpi{e+6bg2%`csDeEM2kg0RZn@22 zay%1pVF4^1@KmA$byBP3o~Ty)=(Uct!tc5@RtXmmaZ;MU4Jg?sbF9**z4Wupp@w1&_csmR8+=jtC8P*8c)^pRdIGW88^qO z@=8tyx|psf8C-)|>-B;|VZQ+|T5K?}1!u`)v4{(gi7UgS6adb>IvxX!ZhM#x_ZBs% z^{8^?T1E;R9&TGSZ4hL88Y#Xp?$RbRk}qGk`joJFYFnGjeFxk&SoUmf$UkY%ogj}Y zcMCK9Gxz*P$veeCP|}8g&foW>c&(jOKJUVFx3?*PF@)BcGj{~FC{^3nM}%=5&S2Ib zSRW~jT-6BOC8=f=5bctaS`OxBpwbyw*4_|M>K+-Q?TpvdD${k%=T|X-xHCq!U?(V}+FHiOg=l_VOWtWyS19=6nm?a8r zlHZdOl%9dRvf)-#(79In?R+10j3-Z@VJ}tS7^UjN zh)PVwS*(oo!d$7Zf}K4^X>g4D084XA6Hl9HM_c_mJ~f1DsaVb zEX!lUvJg%q2Y($06;ik%-#>LdC8g>_lsCxQ&IRk>ov57@)qo6{T7&OEhA`Ne)OL`< zmgk)6`o6J5!i?c%&F5)(Jt3!+hmVP4wM1yww{T6%>6Dm?!)8h38eaQQ=4UMN(-!ld z^J@GrWx2u>>}HRDvgLKO1htujkLjFV&VY|9L;)dT^Ti$G8sA$2jcWs}jFhJFF-i}g z54&2l)PPErCRC1{vN?zVG`!$9AyLhqz=Yy$$|-{v^I^-vtlt89LQP(m$@^=8@l^ZB z`On6OG?$-z-7{{STYp&(9UtsO>jh+;sV7~h2)Wa?+YeNZvi-v+t zKV=c2#2Lg?wZ#;gWVu4fHPq^v*VZq$joIg7ceja<^YveSz`I}XfaBdcaYdL7qL{DT9iHvpovYgyn_ z!k!@VvUm~3H~1?E51lbKYH`f5*l%(=fko%>;_og(fQ;8Fhx4`POEv{P_H{l^^4MZ( z@D4}I@gc-U=?L*5=%U8F zw-^?gZm>yOI|#gEod9PJuamuqoksO)=qfXv79AL%e6e@5nEqq7RoXgN+VIeEnC~TJ zv^uZqvx~}HD`swm31`*%VyqOXH7aofHxSSn6uO zbH&$FLRidR?+eAp$y}T^iN}_sU?yhv1IKm>ij;{s;KFtfQfz_tdC+VT6gw(wKQk** z=|x}_nz!EgC%1rKD4zK-WyCN($Wg0Vu5kMunJL6K4lUas4QaXD^ESZK?zj_8_r7j4 z(1@~A_O7RjTy>YXK3O;Gmudk{995fkmAKk&^VeZhW5zFcw~e@BBLxcDdalI63XX|K zYkgWiW3}MS5znmkX6$Z|)tX{?JLW~h97mdSnQk50cgrJ8(l<$YNL5^h&E(!Nd9Wzu z28TxIB}Jg<9=N^(xV^L{gP&}Tqx1O)po_h7u1yz+e_(ufi@rwcXAtExn&dU`;W8o{ z!Twk>5UDR(ND}GK!_BbwV+Ej1Bt>Gv#&9p6{iJkiO5sw79hXiaeA`Xf9`Bq~CEp%HxyMhkuS;1J+h@H4hT@_v}CW z1YK(njw97#ogfKvELgvEq>%;EzK)=^b1!iVeiTAT=uTas{ zHf8L~m_K9s2+Lj2x!56mR2T*BTKzga)dJH%2aRBmwfb5zGCbQ#y?Uq)T->I{D!+l77A@mGO%sG;6X=qHQxLc^B?WLTCN( z9RQ7c`EK>h^jt*dF#=XJVKgTM4+dc1esNOAH?{^mmQAF)cV?-+T~P18B+B-SsK+SS z$jVz7QJNPTrCEhK5_pblIXDsCY@m{Pc5ArqCKf(K_*PCny-b$e~!xnBh=LnmnYZUIMOPE&j$mbaApPT z2x$1venus&sdnGr{jQ?moXzjr!j(}~wI8FskM?}uekcIxc;=RH*M#G=)qN7q6Ozs^Vw&v1UhR(l*zPtbQsGx21 zuf^oa2flRZGzvkol)N0?xvPNwRyu8yOP;5v65N|=hHDLsrUob4D!A70Hc`lj+z-^> zeWQdGD(uQDV3G#d_d~Ai6X)FS?h}cNl2Q3mBV`Mv7@Kpi>o5CL3jLhM(M0<2u! z?pUJzvRogULROkl42My4g+myH6y`YBYcdlU*6>J3Q^tgF6~_o?h?Pq>$|}L!?;UAA zLi{|})HN6l5Vxxaj#6BWMBy^$W z@c~Z+9v8H{iFX%P%Xz-u`K&PS5+kZ(I)nfIfCEvAsag@AVDC2g+C6gugm354CL&_Q z%{N$-@~ZJmpNr})iy>sw5J%-kPKYcB^+f+YZTjCc&ok-(Cl3|ToV@;LXvH3 zMe0WzsEu7Cm))mA3Kw*RGedxc+Vc)pgmyw473T&^yCzX8(oo=B88RPfYgcv`dhK$!rl{VE5~aB~ed?h#zZnr}`dpU78`pNWxh?|46= zKEX{!o_`Yj6eSpHCX%rOnwij?XiMm~^9O`+)B-#CIjv14{mL!Hq% z70dJ4s>3w*3>)cq``|D)&Z@_- z)}>n?^7wE|=PeOUMOhrmJYzbVlOHZ4X`4$%K-cpqF`D&j#4*K8?bM*>Fib0d-L2g# z-EjL#;kl^UATU*bRuU#gqv)U;UC%NMnt*%~{G&V=IdL^>-IDJP8>JdOfZ#gA0p0oF zu6^}?k03gfOmp9K42S=ecJ6+qN6~A$L4g2+FApRUK+Tkc-OdkC{t1T^C>0kF?^2$C z-cW@m48F&^)1CSGTsh{+7wR*-^D0XxgZsH|V{-F@iCZKoJ9A#9#-*ohZ*i65?#hZulQUNJaZ^Gr*vcUHiLBY#6 z5W2xIQLL)ZZW_1sOIk@?7YfmL9h9;O%;M*?lmQOH#9hYv z(?X79k%Zk$EGJ@?BQ$k_;i9!%`0znhxu-rei>11JZ^9=*l2+OB-Qhcr*i4J}Ygt*< z!!2hl!Oib~YKCX5if?~7ue69S_gw6M_g@CHcaWUGSmnEl!Zr-Ib&nElz$i?}snOKG zyE^{Wvx$Sdp}mB9O@0U;B`6lt>Hl@3K%nLTV) z9tC=x>gXAn=#gvMnGv$$!tbG>R~K$2h9yD|&+(-ap&phxvGJQGYrLOMoLpi;PBz9Y z7Bb=!bjs}F6LK28>BkZ1L_YV|pKt3;py$ux4?)%dm#8nE3!&8yWfwffDsZiZrOk+G zqG6I_i8Z!DjkXPy`aQ42OOinr`oWlNwmw~x{Vo&tbLJES$6%&RxC;7^zp>#>RcKBn zu3}@qkApzNlvEgJhPefZmZm@Xth4Eax z@lN4!D`5DO?9|x9WLn5Pkt9{h*g&|C$-DShE3TZCbD$QdUe*)Ne;vM~=vI zjW9o8#e7x}^jIlnX@T|yN_NR4LzD{C-nKr#-RiYpPvmQY0qteA zL;2{K2T9R6#7YLU^~aXq@@0WelV9N0qw{SGq}l?ov}kz<`0t;i=z;%SpS46i$#xJ^ z^&`^K;{GgRU;^IId7N&+&A&qk>s~!C{v~NZtG?i>o{Mh!SS_8(jG9t0zNScZI z{HOKv6#q(^Iu~uLSly^fj@=Y(VLbyG;~|aJ_?Ff98j}T_d8L~9M$c0nw~H4EhNX6@ z#DjmQ3Y4j{yDe{>@w~53H`@Xbber8dKvWJNqN?qP6^tL4Rey{-&5iNF^zQl^>WP)N zefiahZrM$s-U!Ix%ClQ)qcu1)*!_ZT?FLibWfGgOO+%s>!khi%Su#TjIB&<}{QkQc zfqmdYBpzhg*md+alo3kl4U9tm6?`f*0%J|P0YpI!=~Pa~o)d!M%i><`w7GA%idJ(L z>Rh5h+6#XqMcd1u>f}c$p>{TLO$< z)A0X9ITNZZ5cLihc%Fc^$Z49BR(-qq>YN1mR6jcBlyDm!wr-|XmD34>LIb~|r#AwM zIi%&0^=0cZMi=lH3c~`y2F}|?wlSA&BZ_#g8=lt^Jgkcjb?kVLY6qXW*|m+b2fhgNMi=gN6k2qpuQyD7 zb9(1=-0M`IcI_#&38#waF|oG>Hwmcz_WkZmUkA=_H@4wr-C^V*`XGwwK(Cq{X-X&!$K-ZV+F$bmmm|LIzw$pKsU&`)joll4h?O!I8I0XcY* zC*0`E*0FrA-+z|?rMuC!ft2)o>9_Ac>r1_ko^>goi^)OvGszmSCd4o%g_<9`lguqe zAs+&v%#fPd$&Xt#jb1D`yeCf0@z4^l0ioSus()ObKGSm3+ZyB2MP?pvVSBL`9{aRh?t=iV%n3h&Yc-| z-J)f`BJt)v`V6nfRqX8{g%_-JBt|H)jVVec>&Q=D;68dYZn#yt=DB)Y?S%S?OZL5W zE;Q`bkfmt~tC#tTW?8TKUo6E3BvsCSO}4_sF+43&Qr&mT6xRn0hhwUgxB}!dNf4V^ z%bMSLzw}Frf&L^h?U1!~xm$vV+;-hH3w7E=EBzxCK2|9+0=un&OGJeB6l{y({HP7= zUB!hPS-7Lj&$}zcj0s97Q2xEFX}Kd3ds#0HwjA4L)6TyH%`eXAI?$h+*=}dUqT>#k zA|X@dI$p?zc*GQ<@_KZ7N=m^A1ID|@9(WZ_dF?`O)Yc**B3OUJ{_cu`f)|YeSzfFR zhx})~b4GUrQ49JZjv~(j=$HoW=YQ^womtk*7v&H^uWVVg^A&`v3H!@+n3@oXx2QDaqBzQi|U!kDh`Nvn@mGD3k~%nJgb zF^5wTQ%Z;Pgg_zNN4>%bR;|K`)*J9WkwxaT3MYz{giaqo2NW0E_&C7FSGeNHic6n& z&h8xb25nr3IiUh-Wje&cj8+vA&oxBOld6gEYQ?62U02paZ7b&C-2wZWC!G#l+fS}| z-N>ltD#sI}k!w4r-J{zcE#y3c75#$S$pgL4FyP?6=35!YLLKu zG2C>y44>1hN7b9FJqGjR0iC}eNC8@Q-K4-ew!$k}ELSoJ^y}w8<#K4eE2F;rvSnu&n$li2av1`ja;Ae4hvRXuKeft_VO{)$OvcqQbf}c9Z3|?Dy>uQ8$LaVo3 z>v#MPRPKPM2lciMKuDj=eDy@(s1930@87(I{Ph*1A{n=3i3ULH3uDjqx_5W2`UVJM=gE8q*ZeY&T@ z8J!T57ZamEddJC#3p$c&4bRH1lam*+Ox15D+4euD)!a?Ry?KMHwyls2!_MrlDm&h2 zW-cYg?X7V9lD?pJhj+Y$1@eC273Ag1Y?u$JRK;4}PK0y|pLz!6Sj%X%!#f<(s|l-CMqpbE#0T))D@I8+^P zW8u5LA%>wh z3ui=UsD?39KXRjHlDj-^lKnlc)6vpz34tt?@nS_?=mYXTy{LzDhAu_hODO-gR`%gf zpv9_aW@Vcs`{A*xxp0}@KUFWhWz9=r6fQ!0L(jj@rHx>+%U!_9z<|y_O4k3m-9#}X zR)b|1LIGH!w<5Uz_LX@@A|kpq}Oow6)=|HxS`pn4Ez2)kJ(i1xX{;MH|YqDd|Em_sJ&lM z|52>jREM@Zd3nQ2iAsIN9qP3CX3;91alz5^d_1itds(%vQ5frQ!N~GlBR}yky*s57@}xZLdo9&d zk~5+cSu7F3n$h^lxJQLGx=^qalGn6X{_rGH6>`Ta7ph!L6x!4Q=U^u+ut~VVd@(kJ z3!qb$2q7@gb;!oywRya!Um*o{-JRId;S7=Q`D#-0_2*H339*rIZ60drpP=hO>t#up z-;*77Faf+3l{!0ShXoYIlsEnewdd|)b{Y`v5Q1}ATlR+_*EY7`P68eN{D#r7<(1Rm z<9EMrFtyh?nh<8oIVI&Qlc8VXsvcwKAYOOn0+xsv-m1E^*&;mWwE5c~W7)diU(bqV z)~`hnf?Go&DoK3|ag?H>V)TKqfzR28o}Z$bd%)JCI=U8_Lr5YVqQq7o+H^nBP>{Tq zYZDjJprA^o8mB68XMiQ;!~oc zkeBL=bs<0Filoi!4oQN6Mr_9*_!_3EqJw}!cXkWQ{>A6Wv(F04z(I;|a`)A&g zbWKY6R)plKylnZ+zO@c@uQc{_b))e?uJptdRYr z5#})$v72h^s%RsRd6rq7!__7U52Qrz&uP!8LL7Ab{U-V{v+|X}HvKC)iBwmRF?m|{ z6VG8BhEqLUn4-B`S49%NcejAb|swxSO-7vz7;*4}$_DQ$O^s4`wKKIU+~ z!$PyUJan51C4xR4@#bDKt@P40dGe-QCtto_bZ$78OQDZzjCQj8m>;Y zx@cLG@*D*hd#iT!YYsp2>lbD*(S)@r2n~J4MWHV!72dx`*O5jo`tX7o3#rc@MdJhd z`AeCJxS8B|OzD2k@OMFV8#74*l2KO{6P#fQ;p2TR2TYT=^F^FNgAy!{$+pw%Wc}S} z-RE0Ib#qRK({Oqxhb@KYk!bk>zBf7uudkhX#xt5UHUI=5icG+u#r51ws^yDv;viXa zp6$o@60yn_k$I#m!=g%Bw1eRqEr?b^@8OFSZNItEINaKB4g5ar_f(E%?xqWsN`k_QTfllqvdx2K8((`5IZwy%hx@h;-9-^_2Xi94>) z;((jY_HIRhs*iwVWoN-&o$Qu=9%CVM###SFq8cOX#8d4w@`92u<_s@Tn^rfyF`w|D zPDz%*qyLD*(1pHQg~GPo*cpG2Eh{iw$M9ihDYJ*^dsx?ko$${`EY`)UK9+!f&EThpxXr&oHM8_jJk~S;u66%y z51!4a$JQ zFl{);8MDU-p6nlxG;SGi?`1u`OdKzq%-aUlK$;i(fG=K@1Na&0gh;MvzT~A@liMTB z9terNG#~heYA-aBtcka>sk^3=t=ng`Fxh&%N0t<#7czM^O8~L}8}6+4UzKP}=+9 ze;MuLLQ33myn$yLx=P9e<*zz*@Yv}3+rx*ONA4TnQv17b%Z?yO*Aa?IKk37Soll^SD}YkhQ%XorAdWhZVRq?RlbEJ(-0*T_Z=4kD!4)${LJNZo6)2m(nSRO0 zSgzCwS=7p654u7mT()ZVKcNZJ8eMNP<3((gxVpyE{lDK@ihzY2__sXTwS+wpqmoWH zg{qERuAqA~nac?lWF29KehCOd=Ifmh=+AD_pQMXt*{}&hnt^G3gS{|mzhTnMs&FAQ zRhGF?Vl}^D^*L65ccoV3tkE?8D-%sK|vwm^RB-F&`P`#Dm&fV8a%zgCnt7SLUq0=M~qq(85s1&K#Of;`yMq5N$U{y^w z!ovD5t^delouY`X<*af~Khp_Q*ou}5ZRPt+>>o2UU0DfNRP9h2gHsx`4%8ZFs>4yrdQC)jYl1-cp%4v@R^hTQM)SP7?cK3Y(VSSz^a?K6BHZ zrIlLfYx0%c8q)(6f4w$$8ARu2Xw4T8!yL%g!yeYdpEr(FLf1w(CyO-^^uVQw-VR%# zlF^XiLq8n}30!lP>{a-RV|I=8Vu@!uiyX?E62wsjClX8niXjKB+R2~PrIjrk1ssi! z{WHIknGyr&o<5NOsTlzbiEHpoMui0#<73r$a1gC(tfJB<;=3q)7CsGsbm-lSIP3Z; zXH6T(ebSk1eVHz7!8Pz^S!bjxoMTgKY0IL)JV@Pq4L5QAt@)*@XBG3N9P^`$;TjF&G?q#`#Q6K(?+f4FGlA9yg+^=c{) znZu^0syb~@Q7%f*TPbl7Bn*OLV$^^CvtY%TW7ZaU~Ub^--qQ2>a@eZ&5>L*rH?GLBnj&X#Z#rlcppD zexc#3ncK$2sZ&B2S--m6ce)QBglIch3@XUXvMF%(+*g}C4rXZoy`amz#%$M1Nt@qP zFSF?lZ}#@gv_JlU)$aziJ(t7+JCxq~wMxDge^okY&u9l{=-$o#+{Lg5woG}(aT0t> znDJyvD{h?nKD7y7;(7HS$F77)x!Qw;R$7{yaMFMO!cWeDcWGBZy@C+9z6?g~6efbR z%H4`<(l@SoIL%bS9!SAfp>fw6-=Di=b{XH_3&jy;NL-CVQk6!|iTx0${-2U*kZ$+1 z?sK0(Z|C~`{jw9jg0Q)0-j(8cfz7M|4vxx@z$pT z4_{LswKB4N>kd;Jx)|b4m-j+7^hif|%L)Je0{(NTpb+9&Saqakr3!Z#><-sKn0dNb{ANTr1}DznKn zN%osV$*gQP*1lWuZv}b6ZqBpSRqohQwT;swcdy~s{~eJ0Wh$?(745|W*r;8doT?KB z1_xCErA_`<7%SqQ>ghQR_MUW8+9ARQ@}ZECk>C2=@bIv}UThUxXiLA`hBGlWb+6s@ z-@jtL=Tl9|M~*x7&Y(vHxp(#N<@dve`R1z>xO6j4HnzzV_ke%^xzY6W^qAcmE**E> ztA~^3m9CG(#7X_7u>n2QMm0}q@ElIs-z}CnQZyq-b)CT_7hvU7vL9ngIH8I?VAMvx zHJ{>nz>rcO?Y%Y1YjE#l?lyIP7f)xyYy79KOKis?Os#ZBSO>5Erzpnhc0v`gJ!yn} zX}EUOrCT z_*mpILgrsM(Ww2*AjamGvsg_4(+9?Mw&J!+z8z=oF=~v^ zl8j%9(vEWm1%m48>Y+Un#$|6mRQvy~Ixb%EH#0Z;qb||$8Y|n$Mx@3|SfqX~*g0l$ z8Hpj_afV{!QvnOFaSGqOv{`J4r8XX}dT+ePb#oPRhU;Ok*2{w8(0udRftNSRsR_q> zvw!KZ*Dc+oT4q+g;welUN^i6_XTtXy{`bRi;(R`Aho_=>(F*s7yiT6tLR?zC=M9JY zVjaYkzMb$r9EZs@@0Cjm)|rkPrQank-jPKOvabfqEr6;#fTfEhw zV9T>;P%QVa_p5_<(+V7Gfmz3~K=)*(Su z7?9_Fo@GvpVLDd0jjOjX2WY6sm7_q#O&K#c z(0iLm1_AT~asXN$YAdLr^!AI6ZuKYXhjfPGA<)F}EoyZadmjLIuE*^e43OrrjDo*7 ziT7?>EtGTgp(*A{!9TTF73oxQ9=!rdmgn`LkZNz<*;+4F+v$Bz;+t=tWL=*>B2oJp zbVp>jM&&F1sRNc?*r=FjSio0!Sv>LL0LVN1wzg!YyeyGF|60z~zVCwr_D=*5)<-MS zY$2qeql25-AHfD6l!tdp(*-Q966@UO;r<=yc|pmeW#R6awSs9WAPdKV5Y7?s-NFK4 z3wEMZ7me9;TJ~{xH$Z|aDD9omLZMx9d;u)8&8n;jP zdVKh7HHn^uq^jtdP3UkjZPv83%Wqn^j=h36^EW%8fNnw zwn?Ntdc!?6LD3x9w=`|keBPfeif69_e=0Hz_Gr9^OD`W;K5dAW%W?;QYSXR8%P+*B zdmvP}b?uTIZt~$kLl2}j`3-%0er=RUsCLLVCcHJuzg=?q)mgzKCskbssI?y?TN5=(d>t}xg z+^$<3vCCgJ!=IL{ofqM_PxmTXK?qFnF~CPA5+*Px(C1=*2CmH?4Iz|o`I+7z&*if; zUM^x4w)^-%p7Vn8F9G4Mpxg!&O^U){kV(CeO6<>gCnB*o2~eDbH;-suSAuVB%OqBC z&;3N5*MWQpOQX~H2COHky@3T4efyE-GCnvZh1C-GsEhA`;nxoWE~jU}VM|!cMj&d) z-~<%y4@V$(1_3kDsTRR9sc4F(EZueTgOx&`D*(;f-^jTy0315p-OXeRnf_>pK!M|m z#G>0_6Fqi);ux`I{_4|gds^oR-j8qYAna4~o&dk@Gtl8E-0o*qGNhxzMoB1-zkj`% zO4KR2YEmbD?!A+9=t#r^$_#~QP5{ypuB&L(+|4!>r1I!&M#Ra#V^^7uBC1swX|p$9 zjMw%hvW0DFPlIkq!p@F@Z{yhKzU&(?aL*y&9iVR#`|lef)SAp!jY8HneNNu%x>xtp zH5izrsSA?0u%CgUF#Ya!@sT$Q)OOCx@m}6;ezOzyb@_e+9@OvU5A)VsiFMjG68rB> zvWZRB$pduXr%P9|U#~@W=Q_KC5%3AxEYCIlP)4n)nF`8&{ZHgY39x#|lWaawm}e8u zK{u13_EKi|whAQqy44_yhS`Ibiu|iy@;jBrib#lR?RR`jr#S?@Ga5R z?c_>$LU6=rDIRMPT2lKx+8mKeD=wYwo8oeVSeU2ES*fHeY@7K*PlU6bX}mo7zgDc( zY{`)navH55&;v8BPb#fsXIYO;kr8lbdd2v@TurrEWueNb*t*JhCbaK5iQ(BXqIj*m(ET$Q`JK7h1=#HIFm+H3QACM>K!ATN)v)&$;CaQ^sqVkXH4Jz!>k z-vnipd_RJ^1EjrA`Vn!iF*n3Gv1xiU|dpmWU+r5mv-C6 zl?w~OV+$2~n_nl)ovJ2SC2XlxZSmG-Qrj7ZL^KrH5gVhZUfd(^knd^xoeyxdi6A2Br0ly zu%fc^!|!+4a3Br}A@tlzPqW@F+tg{L^EyUK(|z=O|A|BR`Bbeb2EEmu%hJr^J@(a6 z=C;sHE_k#NOeQK#hdQ&Ra=ubX>T(`A_58E}^V5&T!&aP9PO%Bgq4GQ?&#mU5wQi9QhuvoBU7BIg27_j`6@k3Pw(h|l z6203+S1T|xAnr|MBhgz-$-UDi*i3N;hk$@Fi+YVvjt%yuB>RDvT8_4?n_4VSwf9T$ z#wqXz&9@)*{(L*;m$yAeHF!nK7rVA(>G12#yC#G19dj@$o`cO(c`Irl+$clG>!!02 zNgvC4Fh_k$#>y4zUn6pGkXFza)Hpu7E$QAM8|zDZ%YTkjlbfLFxf{xL@YEvu5*e30 zV2dDD;|s}W%b=2mgZftOAIn?-R%4$LXXz=>t8eDk1b_2z*&>U%X+E2M={c$E#q-qf zu{5r#3lCNcm@d-&8Y>dnuwzxZFBW}KIbU2Ihk4<%+u{A7$&uDjDDzvn039#rYW%_o zvv+BM9S>j<6HX}-sB0w~JumDSQ!}Sy__|YOUQ$P9<1^wHs5+tEo)a{!Y)!G+#n6S1 zQC)+6i7Q&A&7qm~XN+~=9p`_(f9%cI$odg(@6shJu8}MU8g=h?RM!UYQdkq}3I(r= ze^_tySC~x4mY<9?-u(SE-M#xonyFsAVS#Fm#o`<~V)>%M$tv|yO9P6eVg0g4os>dV ztK2GZ86hATu(*Tr$+V#ZUYGC9pex&aj%l#f?8dSokCy{i&+uxz)KAB(fuP&f7r;nshj zIgf(J217#Vg|AlSiZzt(A(}C@_IcWz&a%>*GOb(yF5~L=%F64dg2Iw#1%-v)Co8V} z(v~QWnYNbg4rGdWo4=&O7dMi$7BR~ls#vNxdVbaS2VyxAa5*ApIt_4a!uq2U5#9!U zG4@54YtezX`SY?1;p4uS^%ax6d-fUd3o*mx{jQ{Ndb3z`)nC&8$FX)&$ITD_XS~#& zE#sHJOKDmFenbSJRxO5IfL>}ZH7wqT$~ShP?9Mnkr`>#*DhwX1gAlFWrckr;)SLArNeDQ+|^%LpZVmhv{knFACs3X1w5JwHrt)oF5+ zt^&<)aPnq$XjWjy+c=x`o5o9YA5LP05|o;L582BV|727^&KM{p(L~khDvRgJ_8Ry4 zU>mc-o~`@MEm^?fe}-}G^WkNipM00;?7qO-33DiwfO(bfgMj+%25k$6*u4UkG+#?b zIHkkaA0K(IVz9Y&D^~Ye59Q#G1^lWMgy3?5it@l_txi8g0uS}O_Ymmq27<(~swV-Avh z0d^$KxOAZmPKXNrsTNu&JQuv!U}ZSBXMMPe@=I6+#`Bl9io=V+EBcM+7X8vOdKld9 zMA5=${CLTf&3+>=N>K{2dIb~~Lx1+}rAl}?B@{AlS@M2G8 zKX-NNjWHg1p@z6AIef|#Bc88CJXM+DjfnB^ErunfcIE=C#ubtITyi3jqK zYZ!U;t*f^XYDx$+j8CUQBW+CGy@Qj{wQ$QmdrFe@D9j0&gQT=Yeo zPgONk$W0osDD5ot*7y#4Z2R?LKJv&lrv8(h4#jJYR$1O3O^Jo(E91T@!rh!xrxHE_ zpA2eDM`Icj`07+%^em*DnNReH{8XTwj^Vtu3b~B7BYoLG6%o@>GXEX4ATwG&Y7SZz zYE(c`EWH95UISe~lGh_QM5yB4qEvY|eBScXifd0q+A=YeWJ0Dto(T^a;!KyaF_$%m z(*)f6gG9Sobh>lyi`Tz)HQPsIs0QU{}Vp!#0}#W^U$P zK&#BarlRzWM(fBlPE}Gu5-v!qML;;ItXw7->W;O&heCz>$`Fm`cCX^AY%uYcaW{+w z7r4BF64;qaOQf@%c_yPVsWaCexsu^2K;VzlZg7AH1rGBBNeF3HGTu@HT2xh+E2Kzm z!Q}HPMvnQ-83FSe_TR_+ro~TxxU}Qw;74QZ7nV(6DQx{PsOw&{ux_c5=^sIywf{jf zmZ#pL$AzYeE!`E15F8SLy_&shZ2!?}>L-(^I<{h}K5_PAg=j@ZAz+DAg~Z7)1k@v) zaldvp;jv&wq?)bX+QX$JP~RM}ZCBYj7}asDNwd%Aov>Gz=~@ZPW>i`P2!VdRP2r~8VFm}0~BbVFLC82)IX z;Sge|KCgz)XZ1Z?GUnrRR_keeEh$c?onOU4ouNU)DuFEMy2Jy5_`z!N--CEj7JG9W z0C?5ti{k9j!*DJ;>v~%v@U>4yh%!dI*c|$jgA9$k#*in?FDJOTP?#i0SmIc1t znL&NYR;xuFWCg<28})&e(h8cUy9VYIAB(eUKaBl$RVXBKU}nfnz-Yhip%(r~Y1ZI6 z>zV@GqLf{~dr#~+GwrCU4m5*v`sd>stBbvY*B`TjE8X%h9S$|IRf02J`^*#^nRi1i z%}cl{f#St+xNh_BU+*{DWDtieG6_VpW@b-18+s4j-Fe(gU{hg=nxyV8#Jg>L467lS zufCs=5TYCVsyPS)kzW7;W@`=0|F}?p_Sc5&em6>QS180nMXr z*cJCkTNw$%Xp(g2qQ55;Yehc;B^98v<(_RCOrd2ZmF1s>bqJ{7?LNmucX&`lzf?cm zu4~um3rU~L`tWq}ZfyXlQ`$KvYy<&d5x8XT+nM_GzBd?s5%EEQY+TA7< z9bLa|^gBVA`xy3IB^eLI+vavWjeC>&pNo}m(YMtP?{Ax0drO;fwUn!^=3i@hS3sXJ zK@87(1jj5{tI`G(qI%&)`YTczx2MR-49}vb&9d#Z^vh*fS6Jz3GM7=u#Wf2HeZ(Ud zo*z7R@p-c?xHHjnj*s|^=Ud9N3*3V%YQ~C^9x)3-j#R&DvCi9-oJ3|*WF-|93&By9 zSjhp$=6t;DM3{nt>Zb_X3l9bP7S8~TLBbYPp2Pr!!2$XX5tL5U3%PEQFUECw8AAs8 z37P7JFHF>?*-K|+i{cC&%5j^eq_2u}<(oq+8YZYYgc4J zotj5j3le)qjwnTo=A_qtaRa}`J3&jC$2_YW5t8i9AdTF)5SA)UpNNr+qYooX}bCwArKFD_AGL z+H*uC$n(q8pvbpq7n+PX{l(m@ps!Dh;70d+SQ9o`xFRG}ui{#xBYjG}P`|z1At>yT zrmFs5B?om9obm4x8|W)g2nR;!&Z%)B!uk4oy)pelQckR|FPOdr$G2+JYBj!^QmBHb zKrc=08UHD)r6hl)e4A6#|66m0A-Q|Ga-=%NkMDLX^KGlwM z8?;Aq6Lai{yS>E5!uif=JR2=T{&7?b7(m!?<6reAjcXX1Ik$R5xmSEqr@qa9prfTE z9XSt-Emv)3=Q!q^elva&k>pIE@Mjwj&#ln9h*8$DcjKIy1C@63L#HGQdgK?Vz;W!` zNUZVBi$GCulBk;0kz9L6JRvcSz~x{O8_6Pf_!Uq`B%^TT2uE2r+f*OeIvRV+aRoSp z7VUQXg%-LBa`i*7@{3hwkppg$=s$m&>J@pWNtzKNQEgE0FjiYQX!%iGxN0`e+%mGC zThC6RAhoKrKZtVNzyUQW!o$QtD!HS1_0L-{;{O@EdqQc(JKFcNRmC|4*2U+gbQ*h4k-z>0v4(Lf4~oInT!?N~lNVm{kh~H1a~)w?29WIk769L2Tr))u)J6j={?N6ut~=Ao`7l zR5hxn_q}l4v4T%JW{dI{#x-H8ahDDnv{68><0xv0);y~mm4yfW^k`8rG2h&@GRb(A zomVhqdEatHeX*#?w$qI2PA1x+$W{EV?_)n6zal!Gv64ZoHyw!8+J?sSOe*!^eYo8v z07$`w@@`P10beddkbxSfhyDHeq<`Hl6pNlz$LDSfU&ql>j7tC-JxeQFYs zi7*~uQd-%~tUjIg+GM1blHU43OK(4+>NiJ@?Zh%!q+9m*4`bQy$fbenQn^ffc@##4 zN0LS&nC-&bc*5s^Bo^{lxQ)@vDFrhqlZ4t+h4;_Ow{|#FJiJ6L@<0ydC^loA5w;Ey zwOv}D3yJs_u8Bx0gGB&9871bNM=hPwVi$WbmG2RdQFZ*6vw?9Q1aq4>D$Z0xzEq2K z;P3(N*fMmiT-bbRC5Y}hD#zN-p9FIEnJG~kV|GuwHbkw=5Pa3y4i+;>9!ixGHI%Ul ziiR&%%+6Uhv?y-sY&gBLySFj4ny}|R)ZQ~QQg1}hi<@{IpOtm6W=!As?LxB>*#D16 zwfq;)3-NtIgWDxffPHThS|jTQ%Tk;{7+n3{1V^bsdFZ?5olG=i2nJarde>1Pp5&%o z$ohHDDz{DGJ!XZKmiUQ{f4agG4~?bO zmRP$wfiAioWkcJus{0nyPx|^fDZ>bmp6cIP!B#~w3PZjxra#35nmk=$3}$8U`#{Mm zULutr6v;`=!yf2{zvrZ~3@~!D_s1Ut#)bZmoJUTv|Z;v9d?-o^f zU+mBN2N?7@norZ&DskqVugoy~;!pvAJS4yXBXzfbxZd=a)xKUqqK%@Hvna76Ehyc~ zZ9?t%Mb(m49!VASwK0N)laF!1v zhHe--Rir^0WI(!`ap+LGbA(}#?iLt2&gQ##J?A{<{>#6DRgHuip<1bEI)TIMHph=uH?j&sVvuZ2R1-Gz-EXJHRj1THL1dt@ggPRi>S zT!mb=Xj32TA-~7u873RC7(HdtjR|-$lB|rmRt@MSmU^Zsv$DTV) zWNL;#Mww)!OZi0M7t_)w?ZP(Eo1*yBVb z^WTEqs%F1za>pkeO{x;V6m#-?M^FcDsPXdZx+@4jF_WbL6U38MRpz$eqN=2_4$Mor z>#dKElk>x`T@IRd*h~RdNWe~FO-PGKBw(RMe~>@+JHJkg?RqNp*ro6LI17O%QHpib z`D;jMYTDajgIV3Tu$kdq2j`?h&q^X$R1cZ+>MHT|z=nwV2BDB~DXvUTanVQEkYEMb zGx+*PEf$!}r05`vMXCGNG|-2DJ}P{y)bLZ4f9X*+5T=c_HHDd`{$Jb=ImYllWHwNJuJEJMg&N#|paV3PJuS?z4(xGtwnB z{D+=gwku8ra!z+R8YHT)s_(!0LKb*Tyq?6iy080V0~O2oRK8G6>3zN=8=lMF-3d}6aHmK%qf1^n;>$-6B4)x0} zyP=q-{7_L#r5oiuSIqgsH|fA zC`;Gy`EQdG|TMqjHgXUkCwiKst+e3p{o2&D1b1AxM!=5Svha(VQp!92}DM$*+t zgG6ESVmvwy?U;s6-dWgTw=_1dp1U+d6pj=u1j&4_N|VTx?oF*!AqOe~MI3d=nQH6I2HsqT)@_nb@&WV< zG4)#VvDDkcju7_L*cgry(qBz$!`j7GU|w2gCrJ zP_of_v^5+YICz{@2Bk3$Wk%P8wnW}7OluVl^KPNp2W!pO8rlES>YW`kPh3#62Q2{{ z_Omtj(ThNa1K9g%wG=Koq?k7R@is|)ff;Dm-hZnA;6zn}E+^Fhb%nQob2>Ny?mLqH zHq75ws(BthpgP86!hg_mETMnNiYLHMui}q%2)Z5Ve7)W^#6-4yPeaeSND{`g*$t&l z2YW5}VA}jH1-l3twOVPL9<`mdYK8zLIeMzG=RGwfpc4U#Hm-mY@b4aW0w*}gb4a{% z%a#m~s!RK>UZm+U>-a2q=bi(_UkkGzuYFwYkC@2DFRiTXcSYtXT{??dt^z!u!`C_%&3{0@I2}O3=iLM<{U%-3+v%J!gyL0n$iZj{7aFUa<(F*KROPgf#vxO~MBzvaRKj(a>h% zss~1%5ConiBd=B#?H&@0-T0th2i`UM>MFgJHWG%i51A{j3G-QEutL>QuK`{h(n|%F zuUy2>UUCHY?MUxtFIRQKcJYF`KQIjq# z%|`koQ)li=sfr9-pxrVGJ*DlodH2R3>hJz{MXsyFNFYB>!Ac&j8 z=jiHPVo%IR_NXZ_KqQ5Oy%~)whUV0WBErAW!;jdZ4vW(o(pSJ?bdK|&m`*pmFr%~3 z{>*8ew_Kz%+Uo0($Q@QnEuTl{K( z2InxwBSHF;zmpgbVR5Tf4r1_{4+C9-O zdOBl~!=hcYM$z4x>9d|Lg`i5d=lCv}JHlF5Mr0f9Aq(+8>X#zHDX=1nD>jU?t9n)S z;*bCGA+YEATH}G;m1LY4YF6qD92ZO?1b)5T@~w8};d7qHTi2tIW$IC6yHHQVt>Xmp zhL?7ae(EgD2i@Jg<}yNX!->e^Sqrv+paAst;$3F?Opk=WP{?g2iBtyu`0Y-;&+~4q zCzqJYyg~DotAolmb;b0$F+bx1Pu?7@wI*VH`ZWIs&^O?KDmvx7F_E>u;w^7d5B{T+ z{J?*REW(V9yMW#0|NY~-S2`=>nKx&cw2ggvXH$l;hE=?&?md0uu%Wh2t)}pzZ0j`F-+Z(sq;y{WsMWzD> zTO(C1Ygh2HIN{^+M#Zz(b*$kDUm~e!H%FB~@l183Trz`5ahAgJr=-w#q(Y4ICx(+l zK0qHgW{;c#Pb02kR3UlHuOIr>Q~1Z$Vpk;b68pe}O&b|PI9bT7ur2RuU|!T^%b55r z>t|^rie1Nf^U1(!k&r<^vGu1O1L5M>?7%UW8qlB)FwLsGi`(}@%M|kJcNO`S$wpDp z00$~?KMRNl6u^q%6A=R?KJ7QBPgUU}e!C>(AeJbHUL&w(xhvqK2?nMX{4K5mbKUFU zkpliOr{A8Kv7(nY)B)CK`yxY{$W^wA5}XShXzM&hUyFmf(#VaEbO z*qz@0nufpd^^%F#6R(}c=^~GC641kD8UzKF@)?JwFrJx?>>_?3B?stthD|$tGzng; z={BF#4hB!Eh*1DCpg^^Lpv!>akQy*jWBY5QvNb<06yKGgFu~Mjr8st9#;a^OQdksP zxKMHNkEq4w#ky9GN~w@&#vljcXwT-`!?XjBt%k8x8Hp1~P0tU_Iv%25;vdfq$BY8W zH^_$9)(=#K_MjaN+%{^qm#q6-jUa|!8stm4p;5uzibP?QI?P?kI$B)=)rl&?|L}Xv z=H$FA54Y`Oz1v+?*ZYmOg6Nf`_M8n_!nF+gCg`q#alIEQbPrU)6(4L#Ma$LZ`xv~ zET`C-Q)4;MBYB%FBP`A#@Uv6MMxucVOEb6ow#Xl|NQGbe9C4HkapUv~wSD6sEs}juego$;JDHQv<(scX!m&iyAv(GgG6plFE$o}c= z=(i(JT1)u|XQ!L+%5==nPYTs%l_`{OO4=skc{G-{PdC6nZU=k`3qzTI_dXy zNR?ya(*}XCAH0ilxk=lbuN9+_Blf-0bJbJD8mW<(Kv3Vlj?vrFkB}J;BKTNaXV<@2 zKyN!yiKW#A`)AY+%-_rz0p(P@y*UU{6|KmDKQ&NJyESgB|0f)zxnyvAlW4ORxjG7+wQh2e9H7VN%3;$_MhmfbF8oH5i*iF^lH$Vip&!cn~I{=;gkU7C! zMuxl!g-+6dQIG-qBO$C`ogFf2L`POJvER7BeJC~9KD)lOm92ck-Wz2-x-fjgs`S=3 z`N8EC{TW-;W5T8+ALJhDWUh>xBlve987)8S$gL@+QXF4{C?JNyOFjuHGTr&q zRnBcKCMU=n8o}r;);p9MC_QxP^4jyx&peEAY&vC7o(We^@)UK3s=P^EEtUs?l?|Lp z;Z<^3*|<(h{r%evk2H?rKScsCem{8fDoPV}Q+U7{WhFc23!lM`3Y|*fHJ={Y{wnD} z4n>jHSVK`YvkGNPb+?=_C*GnwFwwY=_OHfWCFajVJsIyoS+VS~teP7tsvB#M9h;#s z0jlN*<*TyRmEG~(Yl|ykU##BpB9Xw~ms%UqM!#~}pxh26>B>Cy?j^01q*^Hg|Du5% z_u6HP_YACzuOpwf-Gy9*XfdI;h+PCM?$(W9H0`zdg^OvQ{!k|4dm#-Ppf&$Vw$dqR z{ESMZ$t#YejXx(C?01$g_iI(hoxXo{rtpoELNiNb~D zw&7KQE?yy-Co?=@ENeujs)H@w<^Gk_S zT950hj!U7}Y}bz|)E?Al8-uA2<$_gfz>01TFuG-sqq0Mp<0uV#zu=}b zKe{lJXwfKlJNsTf^HBHE4@=6LC5H9+mSQt!;JMy_{}uYNXYTLxp9|!Bg9Z^>MNn(@>CK ztOYnM^u#O_`VlD^p?4M~(MW^nhiW2tJX~LJ1pPo;oNmA60fft=VV<5g3n2^#x=2{_ z1E3NKgNV(LfSQDG!62jZA;t;S^Zmm4R^RlrNy9+4(Ev++i41X$I{ddX-_AstPRh9b zFHYjqN0%yFaenTbcu+~>iSN{AGO7`aZv3{?_DDDEwhpL-!Y&eX?ZU-oE1!nDrejL$Fp@ahFU%Z)|&i zaz)ACm~abjLB2{Mt&d6-ckEK5O2{J0=f{4O6TR(^2qZj<|2rz)+lLMhHoGBM*d{<_ zWcW)d&d_^Igyr1hA@HZQd|6}5gm-k4;I9$6^nH;8=6n&%P1}Y}31MANlwo)xVhe7C zq=h1#<~b=^voEMCzr*O;mnjF+e66sK(oATmtXID$B1XK3h3Jz~_W^Ah7O4Bp=vSU7 zhJ`E;ils9@n#9dgXG9o81ywKRb(-!$BR-0T2^%JamL`f!F`PO)a!nxXto|(6Y-er} zlXs4old~K&-SUGgw==!Xt*D5JCgQWw=iDo(BR2nBpOg=jI;sT6_e_II{S6aT0H=YC`AgD1Pku5dSq)#X47G#H0C2b$^KO zvoF?D#PgL}i>F_zFx1q%N^i<#pTtF0X7^*?KR{Fj!L!M7`tbIkpzZClU99u6v8?^M zv+)g0jD7#Jabor7fwwnrk(*i0BLPYM8D!c5UJJfEtkkMLJEGJWiY$2$xz(gMsGRF~ z$5Z9OQ^JW>T5!l|MtI!MB!atV!?efoFho-!V-Y$17c_xtK zIOU#j1tquSDl0g3oN5sLE2VS+#Jo$USLf;#jB8&79cDO8$Fjwx<{JjM>DuxGZ?FK( z*2DNa@f2J&f~EFXg{KSX>7)Hwc{eNAy) z7!iv2amCJEViA0i)Im|l>q~EP-sHav{0Fb}2aSo10Pmmxt+sD}-k3MAU*S?~z zrap#)Y`q={&T;uLnoLEJ6fNr6Jx3FLihPh@eZ{QOx;?a4m%@QgF5^cH8@9m_6fqW=;pwX zukIo?+D7R@8$}hKDgQBTsv}+4PVdg#Eh!Yyiq!+X3|KuMZH-HCFv)rO-ZS@!Upvq> z^7qh>S$U7cI?zXbsiABZ0*gv)2$KsrXQ|`)FYz(g<#mSqeK&7KUUoGJq}Uy&WFEWl zi?SpC3`e$m^0zUbjgM@w?w`e@|ApjkG5;0K1pSNC`Q!inA%ArlOMk!cf8O=qE*^^g n>odIjcSrpHy?DO9e2301cf|Q5<15<(;3F@sB2_72`r*F-Y*b2; literal 0 HcmV?d00001