Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Showing
261 changed files
with
439 additions
and
427 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| --- | ||
| "@gradio/wasm": patch | ||
| --- | ||
|
|
||
| fix:Lite: Add a break statement |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| --- | ||
| "@gradio/client": patch | ||
| "gradio": patch | ||
| --- | ||
|
|
||
| fix:Ensure websocket polyfill doesn't load if there is already a `global.Webocket` property set |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| --- | ||
| "gradio": minor | ||
| --- | ||
|
|
||
| feat:Added dimensionality check to avoid bad array dimensions |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| --- | ||
| "gradio": patch | ||
| --- | ||
|
|
||
| fix:Define Font.__repr__() to be printed in the doc in a readable format |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| --- | ||
| "gradio": minor | ||
| --- | ||
|
|
||
| feat:Fix curly brackets in docstrings |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| --- | ||
| "gradio": patch | ||
| --- | ||
|
|
||
| fix:Remove deprecation warning from `gr.update` and clean up associated code |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| --- | ||
| "@gradio/markdown": patch | ||
| "gradio": patch | ||
| --- | ||
|
|
||
| fix:Fix Dataframe `line_breaks` |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| --- | ||
| "gradio": minor | ||
| --- | ||
|
|
||
| feat:Fix type the docstring of the Code component |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1 @@ | ||
| {"cells": [{"cell_type": "markdown", "id": 302934307671667531413257853548643485645, "metadata": {}, "source": ["# Gradio Demo: Echocardiogram-Segmentation"]}, {"cell_type": "code", "execution_count": null, "id": 272996653310673477252411125948039410165, "metadata": {}, "outputs": [], "source": ["!pip install -q gradio -f https://download.pytorch.org/whl/torch_stable.html numpy matplotlib wget torch torchvision "]}, {"cell_type": "code", "execution_count": null, "id": 288918539441861185822528903084949547379, "metadata": {}, "outputs": [], "source": ["# Downloading files from the demo repo\n", "import os\n", "!wget -q https://github.com/gradio-app/gradio/raw/main/demo/Echocardiogram-Segmentation/img1.jpg\n", "!wget -q https://github.com/gradio-app/gradio/raw/main/demo/Echocardiogram-Segmentation/img2.jpg"]}, {"cell_type": "code", "execution_count": null, "id": 44380577570523278879349135829904343037, "metadata": {}, "outputs": [], "source": ["import os\n", "import numpy as np\n", "import torch\n", "import torchvision\n", "import wget \n", "\n", "\n", "destination_folder = \"output\"\n", "destination_for_weights = \"weights\"\n", "\n", "if os.path.exists(destination_for_weights):\n", " print(\"The weights are at\", destination_for_weights)\n", "else:\n", " print(\"Creating folder at \", destination_for_weights, \" to store weights\")\n", " os.mkdir(destination_for_weights)\n", " \n", "segmentationWeightsURL = 'https://github.com/douyang/EchoNetDynamic/releases/download/v1.0.0/deeplabv3_resnet50_random.pt'\n", "\n", "if not os.path.exists(os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL))):\n", " print(\"Downloading Segmentation Weights, \", segmentationWeightsURL,\" to \",os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL)))\n", " filename = wget.download(segmentationWeightsURL, out = destination_for_weights)\n", "else:\n", " print(\"Segmentation Weights already present\")\n", "\n", "torch.cuda.empty_cache()\n", "\n", "def collate_fn(x):\n", " x, f = zip(*x)\n", " i = list(map(lambda t: t.shape[1], x))\n", " x = torch.as_tensor(np.swapaxes(np.concatenate(x, 1), 0, 1))\n", " return x, f, i\n", "\n", "model = torchvision.models.segmentation.deeplabv3_resnet50(pretrained=False, aux_loss=False)\n", "model.classifier[-1] = torch.nn.Conv2d(model.classifier[-1].in_channels, 1, kernel_size=model.classifier[-1].kernel_size)\n", "\n", "print(\"loading weights from \", os.path.join(destination_for_weights, \"deeplabv3_resnet50_random\"))\n", "\n", "if torch.cuda.is_available():\n", " print(\"cuda is available, original weights\")\n", " device = torch.device(\"cuda\")\n", " model = torch.nn.DataParallel(model)\n", " model.to(device)\n", " checkpoint = torch.load(os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL)))\n", " model.load_state_dict(checkpoint['state_dict'])\n", "else:\n", " print(\"cuda is not available, cpu weights\")\n", " device = torch.device(\"cpu\")\n", " checkpoint = torch.load(os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL)), map_location = \"cpu\")\n", " state_dict_cpu = {k[7:]: v for (k, v) in checkpoint['state_dict'].items()}\n", " model.load_state_dict(state_dict_cpu)\n", "\n", "model.eval()\n", "\n", "def segment(input):\n", " inp = input\n", " x = inp.transpose([2, 0, 1]) # channels-first\n", " x = np.expand_dims(x, axis=0) # adding a batch dimension \n", " \n", " mean = x.mean(axis=(0, 2, 3))\n", " std = x.std(axis=(0, 2, 3))\n", " x = x - mean.reshape(1, 3, 1, 1)\n", " x = x / std.reshape(1, 3, 1, 1)\n", " \n", " with torch.no_grad():\n", " x = torch.from_numpy(x).type('torch.FloatTensor').to(device)\n", " output = model(x) \n", " \n", " y = output['out'].numpy()\n", " y = y.squeeze()\n", " \n", " out = y>0 \n", " \n", " mask = inp.copy()\n", " mask[out] = np.array([0, 0, 255])\n", " \n", " return mask\n", "\n", "import gradio as gr\n", "\n", "i = gr.Image(shape=(112, 112), label=\"Echocardiogram\")\n", "o = gr.Image(label=\"Segmentation Mask\")\n", "\n", "examples = [[\"img1.jpg\"], [\"img2.jpg\"]]\n", "title = None #\"Left Ventricle Segmentation\"\n", "description = \"This semantic segmentation model identifies the left ventricle in echocardiogram images.\"\n", "# videos. Accurate evaluation of the motion and size of the left ventricle is crucial for the assessment of cardiac function and ejection fraction. In this interface, the user inputs apical-4-chamber images from echocardiography videos and the model will output a prediction of the localization of the left ventricle in blue. This model was trained on the publicly released EchoNet-Dynamic dataset of 10k echocardiogram videos with 20k expert annotations of the left ventricle and published as part of \u2018Video-based AI for beat-to-beat assessment of cardiac function\u2019 by Ouyang et al. in Nature, 2020.\"\n", "thumbnail = \"https://raw.githubusercontent.com/gradio-app/hub-echonet/master/thumbnail.png\"\n", "gr.Interface(segment, i, o, examples=examples, allow_flagging=False, analytics_enabled=False, thumbnail=thumbnail, cache_examples=False).launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5} | ||
| {"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: Echocardiogram-Segmentation"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio -f https://download.pytorch.org/whl/torch_stable.html numpy matplotlib wget torch torchvision "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["# Downloading files from the demo repo\n", "import os\n", "!wget -q https://github.com/gradio-app/gradio/raw/main/demo/Echocardiogram-Segmentation/img1.jpg\n", "!wget -q https://github.com/gradio-app/gradio/raw/main/demo/Echocardiogram-Segmentation/img2.jpg"]}, {"cell_type": "code", "execution_count": null, "id": "44380577570523278879349135829904343037", "metadata": {}, "outputs": [], "source": ["import os\n", "import numpy as np\n", "import torch\n", "import torchvision\n", "import wget \n", "\n", "\n", "destination_folder = \"output\"\n", "destination_for_weights = \"weights\"\n", "\n", "if os.path.exists(destination_for_weights):\n", " print(\"The weights are at\", destination_for_weights)\n", "else:\n", " print(\"Creating folder at \", destination_for_weights, \" to store weights\")\n", " os.mkdir(destination_for_weights)\n", " \n", "segmentationWeightsURL = 'https://github.com/douyang/EchoNetDynamic/releases/download/v1.0.0/deeplabv3_resnet50_random.pt'\n", "\n", "if not os.path.exists(os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL))):\n", " print(\"Downloading Segmentation Weights, \", segmentationWeightsURL,\" to \",os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL)))\n", " filename = wget.download(segmentationWeightsURL, out = destination_for_weights)\n", "else:\n", " print(\"Segmentation Weights already present\")\n", "\n", "torch.cuda.empty_cache()\n", "\n", "def collate_fn(x):\n", " x, f = zip(*x)\n", " i = list(map(lambda t: t.shape[1], x))\n", " x = torch.as_tensor(np.swapaxes(np.concatenate(x, 1), 0, 1))\n", " return x, f, i\n", "\n", "model = torchvision.models.segmentation.deeplabv3_resnet50(pretrained=False, aux_loss=False)\n", "model.classifier[-1] = torch.nn.Conv2d(model.classifier[-1].in_channels, 1, kernel_size=model.classifier[-1].kernel_size)\n", "\n", "print(\"loading weights from \", os.path.join(destination_for_weights, \"deeplabv3_resnet50_random\"))\n", "\n", "if torch.cuda.is_available():\n", " print(\"cuda is available, original weights\")\n", " device = torch.device(\"cuda\")\n", " model = torch.nn.DataParallel(model)\n", " model.to(device)\n", " checkpoint = torch.load(os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL)))\n", " model.load_state_dict(checkpoint['state_dict'])\n", "else:\n", " print(\"cuda is not available, cpu weights\")\n", " device = torch.device(\"cpu\")\n", " checkpoint = torch.load(os.path.join(destination_for_weights, os.path.basename(segmentationWeightsURL)), map_location = \"cpu\")\n", " state_dict_cpu = {k[7:]: v for (k, v) in checkpoint['state_dict'].items()}\n", " model.load_state_dict(state_dict_cpu)\n", "\n", "model.eval()\n", "\n", "def segment(input):\n", " inp = input\n", " x = inp.transpose([2, 0, 1]) # channels-first\n", " x = np.expand_dims(x, axis=0) # adding a batch dimension \n", " \n", " mean = x.mean(axis=(0, 2, 3))\n", " std = x.std(axis=(0, 2, 3))\n", " x = x - mean.reshape(1, 3, 1, 1)\n", " x = x / std.reshape(1, 3, 1, 1)\n", " \n", " with torch.no_grad():\n", " x = torch.from_numpy(x).type('torch.FloatTensor').to(device)\n", " output = model(x) \n", " \n", " y = output['out'].numpy()\n", " y = y.squeeze()\n", " \n", " out = y>0 \n", " \n", " mask = inp.copy()\n", " mask[out] = np.array([0, 0, 255])\n", " \n", " return mask\n", "\n", "import gradio as gr\n", "\n", "i = gr.Image(shape=(112, 112), label=\"Echocardiogram\")\n", "o = gr.Image(label=\"Segmentation Mask\")\n", "\n", "examples = [[\"img1.jpg\"], [\"img2.jpg\"]]\n", "title = None #\"Left Ventricle Segmentation\"\n", "description = \"This semantic segmentation model identifies the left ventricle in echocardiogram images.\"\n", "# videos. Accurate evaluation of the motion and size of the left ventricle is crucial for the assessment of cardiac function and ejection fraction. In this interface, the user inputs apical-4-chamber images from echocardiography videos and the model will output a prediction of the localization of the left ventricle in blue. This model was trained on the publicly released EchoNet-Dynamic dataset of 10k echocardiogram videos with 20k expert annotations of the left ventricle and published as part of \u2018Video-based AI for beat-to-beat assessment of cardiac function\u2019 by Ouyang et al. in Nature, 2020.\"\n", "thumbnail = \"https://raw.githubusercontent.com/gradio-app/hub-echonet/master/thumbnail.png\"\n", "gr.Interface(segment, i, o, examples=examples, allow_flagging=False, analytics_enabled=False, thumbnail=thumbnail, cache_examples=False).launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5} |
Oops, something went wrong.