Spaces:
Running
on
Zero
Running
on
Zero
File size: 6,576 Bytes
2d9a728 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 |
{
"cells": [
{
"cell_type": "markdown",
"id": "f86bc499",
"metadata": {},
"source": [
"## download ViCILP weights and put its pth file in viclip folder. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "e7a90379-d9ee-45d9-9073-7ed5132fa6b1",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/mnt/petrelfs/wangyi/.conda/envs/pt13/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"import numpy as np\n",
"import os\n",
"import cv2\n",
"\n",
"from viclip import get_viclip, retrieve_text, _frame_from_video"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a425a5da-ceaf-4b89-9845-c8ba576902d8",
"metadata": {},
"outputs": [],
"source": [
"video = cv2.VideoCapture('example1.mp4')\n",
"frames = [x for x in _frame_from_video(video)]"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "e6c1cd7a",
"metadata": {},
"outputs": [],
"source": [
"# modify xxx to the path of the pretrained model\n",
"model_cfgs = {\n",
" 'viclip-l-internvid-10m-flt': {\n",
" 'size': 'l',\n",
" 'pretrained': 'xxx/ViCLIP-L_InternVid-FLT-10M.pth',\n",
" },\n",
" 'viclip-l-internvid-200m': {\n",
" 'size': 'l',\n",
" 'pretrained': 'xxx/ViCLIP-L_InternVid-200M.pth',\n",
" },\n",
" 'viclip-b-internvid-10m-flt': {\n",
" 'size': 'b',\n",
" 'pretrained': 'xxx/ViCLIP-B_InternVid-FLT-10M.pth',\n",
" },\n",
" 'viclip-b-internvid-200m': {\n",
" 'size': 'b',\n",
" 'pretrained': 'xxx/ViCLIP-B_InternVid-200M.pth',\n",
" },\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "3fb7397a-02ef-41b5-9ffe-f2363b277778",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/mnt/petrelfs/wangyi/.conda/envs/pt13/lib/python3.9/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None\n",
" warnings.warn(\"None of the inputs have requires_grad=True. Gradients will be None\")\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"text: A man in a gray sweater plays fetch with his dog in the snowy yard, throwing a toy and watching it run. ~ prob: 0.8333\n",
"text: A playful dog and its owner wrestle in the snowy yard, chasing each other with joyous abandon. ~ prob: 0.1266\n",
"text: A pet dog excitedly runs through the snowy yard, chasing a toy thrown by its owner. ~ prob: 0.0368\n",
"text: A person dressed in a blue jacket shovels the snow-covered pavement outside their house. ~ prob: 0.0030\n",
"text: A playful dog slides down a snowy hill, wagging its tail with delight. ~ prob: 0.0003\n"
]
}
],
"source": [
"text_candidates = [\"A playful dog and its owner wrestle in the snowy yard, chasing each other with joyous abandon.\",\n",
" \"A man in a gray coat walks through the snowy landscape, pulling a sleigh loaded with toys.\",\n",
" \"A person dressed in a blue jacket shovels the snow-covered pavement outside their house.\",\n",
" \"A pet dog excitedly runs through the snowy yard, chasing a toy thrown by its owner.\",\n",
" \"A person stands on the snowy floor, pushing a sled loaded with blankets, preparing for a fun-filled ride.\",\n",
" \"A man in a gray hat and coat walks through the snowy yard, carefully navigating around the trees.\",\n",
" \"A playful dog slides down a snowy hill, wagging its tail with delight.\",\n",
" \"A person in a blue jacket walks their pet on a leash, enjoying a peaceful winter walk among the trees.\",\n",
" \"A man in a gray sweater plays fetch with his dog in the snowy yard, throwing a toy and watching it run.\",\n",
" \"A person bundled up in a blanket walks through the snowy landscape, enjoying the serene winter scenery.\"]\n",
"\n",
"cfg = model_cfgs['viclip-l-internvid-10m-flt']\n",
"model_l = get_viclip(cfg['size'], cfg['pretrained'])\n",
"texts, probs = retrieve_text(frames, text_candidates, models=model_l, topk=5)\n",
"\n",
"for t, p in zip(texts, probs):\n",
" print(f'text: {t} ~ prob: {p:.4f}')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "a2969ba6-19d0-4893-b071-b82fa046c312",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"text: A playful dog and its owner wrestle in the snowy yard, chasing each other with joyous abandon. ~ prob: 0.8192\n",
"text: A man in a gray sweater plays fetch with his dog in the snowy yard, throwing a toy and watching it run. ~ prob: 0.1084\n",
"text: A pet dog excitedly runs through the snowy yard, chasing a toy thrown by its owner. ~ prob: 0.0676\n",
"text: A playful dog slides down a snowy hill, wagging its tail with delight. ~ prob: 0.0047\n",
"text: A person dressed in a blue jacket shovels the snow-covered pavement outside their house. ~ prob: 0.0002\n"
]
}
],
"source": [
"cfg = model_cfgs['viclip-b-internvid-10m-flt']\n",
"model_b = get_viclip(cfg['size'], cfg['pretrained'])\n",
"texts, probs = retrieve_text(frames, text_candidates, models=model_b, topk=5)\n",
"\n",
"for t, p in zip(texts, probs):\n",
" print(f'text: {t} ~ prob: {p:.4f}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ebdae1be-0dc4-4f3c-9856-5e0fd27aa368",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|