File size: 3,568 Bytes
6620552 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\iitsi\\anaconda3\\lib\\site-packages\\gradio\\blocks.py:503: UserWarning: Cannot load huggingface. Caught Exception: The space huggingface does not exist\n",
" warnings.warn(f\"Cannot load {theme}. Caught Exception: {str(e)}\")\n",
"c:\\Users\\iitsi\\anaconda3\\lib\\site-packages\\gradio\\deprecation.py:40: UserWarning: `layout` parameter is deprecated, and it has no effect\n",
" warnings.warn(value)\n",
"ERROR: [Errno 10048] error while attempting to bind on address ('127.0.0.1', 7864): only one usage of each socket address (protocol/network address/port) is normally permitted\n"
]
}
],
"source": [
"import gradio as gr\n",
"from transformers import pipeline\n",
"\n",
"model_names = [\n",
" \"apple/mobilevit-small\",\n",
" \"facebook/deit-base-patch16-224\",\n",
" \"facebook/convnext-base-224\",\n",
" \"google/vit-base-patch16-224\",\n",
" \"google/mobilenet_v2_1.4_224\",\n",
" \"microsoft/resnet-50\",\n",
" \"microsoft/swin-base-patch4-window7-224\",\n",
" \"microsoft/beit-base-patch16-224\",\n",
" \"nvidia/mit-b0\",\n",
" \"shi-labs/nat-base-in1k-224\",\n",
" \"shi-labs/dinat-base-in1k-224\",\n",
"]\n",
"\n",
"\n",
"def process(image_file, top_k):\n",
" labels = []\n",
" for m in model_names:\n",
" p = pipeline(\"image-classification\", model=m)\n",
" pred = p(image_file)\n",
" labels.append({x[\"label\"]: x[\"score\"] for x in pred[:top_k]})\n",
" return labels\n",
"\n",
"\n",
"# Inputs\n",
"image = gr.Image(type=\"filepath\", label=\"Upload an image\")\n",
"top_k = gr.Slider(minimum=1, maximum=5, step=1, value=5, label=\"Top k classes\")\n",
"\n",
"# Output\n",
"labels = [gr.Label(label=m) for m in model_names]\n",
"\n",
"description = \"This Space lets you quickly compare the most popular image classifiers available on the hub, including the recent NAT and DINAT models. All of them have been fine-tuned on the ImageNet-1k dataset. Anecdotally, the three sample images have been generated with a Stable Diffusion model :)\"\n",
"\n",
"iface = gr.Interface(\n",
" theme=\"huggingface\",\n",
" description=description,\n",
" layout=\"horizontal\",\n",
" fn=process,\n",
" inputs=[image, top_k],\n",
" outputs=labels,\n",
" examples=[\n",
" [\"bike.jpg\", 5],\n",
" [\"car.jpg\", 5],\n",
" [\"food.jpg\", 5],\n",
" ],\n",
" allow_flagging=\"never\",\n",
")\n",
"\n",
"iface.launch()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.13"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "a10896378c7586fe060a2352f1f55c7416a5095f8b10e25e98ff567d7ae9c79d"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|