File size: 4,837 Bytes
1801c3b |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/sidneyradcliffe/miniforge3/envs/semvideo-hackathon-230523/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": [
"from tqdm import tqdm\n",
"\n",
"import pandas as pd\n",
"import cv2\n",
"from PIL import Image\n",
"import numpy as np\n",
"\n",
"from pipeline.clip_wrapper import ClipWrapper, MODEL_DIM\n",
"from pipeline.download_videos import VIDEO_DIR, REPO_ROOT, DATA_DIR\n",
"\n",
"FRAME_EXTRACT_RATE_SECONDS = 5 # Extract a frame every 5 seconds\n",
"IMAGES_DIR = DATA_DIR / \"images\"\n",
"\n",
"DATAFRAME_PATH = DATA_DIR / \"dataset.parquet\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"clip_wrapper = ClipWrapper()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def get_clip_vectors(video_path):\n",
" cap = cv2.VideoCapture(str(video_path))\n",
" num_video_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))\n",
" fps = int(cap.get(cv2.CAP_PROP_FPS))\n",
" extract_every_n_frames = FRAME_EXTRACT_RATE_SECONDS * fps\n",
" for frame_idx in tqdm(range(num_video_frames), desc=\"Running CLIP on video\"):\n",
" ret, frame = cap.read()\n",
" if frame_idx % extract_every_n_frames != 0:\n",
" continue\n",
" image = Image.fromarray(frame[..., ::-1])\n",
" clip_vector = clip_wrapper.images2vec([image]).squeeze().numpy()\n",
" timestamp_secs = frame_idx / fps\n",
" yield clip_vector, image, timestamp_secs, frame_idx\n",
" cap.release()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Running CLIP on video: 100%|██████████| 7465/7465 [00:04<00:00, 1759.86it/s]\n",
"Running CLIP on video: 100%|██████████| 6056/6056 [00:03<00:00, 1728.62it/s]\n",
"Running CLIP on video: 100%|██████████| 5234/5234 [00:03<00:00, 1648.12it/s]\n",
"Running CLIP on video: 100%|██████████| 3551/3551 [00:01<00:00, 1806.30it/s]\n",
"Running CLIP on video: 100%|██████████| 5904/5904 [00:03<00:00, 1655.01it/s]\n",
"Processing videos: 100%|██████████| 5/5 [00:16<00:00, 3.30s/it]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Saving data to /Users/sidneyradcliffe/repos/semvideo-hackathon-230523/data/dataset.parquet\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"results = []\n",
"for i, video_path in enumerate(\n",
" tqdm(list(VIDEO_DIR.glob(\"*.mp4\")), desc=\"Processing videos\")\n",
"):\n",
" video_id = video_path.stem\n",
" extracted_images_dir = IMAGES_DIR / video_id\n",
" extracted_images_dir.mkdir(exist_ok=True, parents=True)\n",
" for clip_vector, image, timestamp_secs, frame_idx in get_clip_vectors(video_path):\n",
" image_path = extracted_images_dir / f\"{frame_idx}.jpg\"\n",
" image.save(image_path)\n",
" results.append(\n",
" [\n",
" video_id,\n",
" frame_idx,\n",
" timestamp_secs,\n",
" str(image_path.relative_to(REPO_ROOT)),\n",
" *clip_vector,\n",
" ]\n",
" )\n",
"df = pd.DataFrame(\n",
" results,\n",
" columns=[\"video_id\", \"frame_idx\", \"timestamp\", \"image_path\"]\n",
" + [f\"dim_{i}\" for i in range(MODEL_DIM)],\n",
")\n",
"print(f\"Saving data to {DATAFRAME_PATH}\")\n",
"df.to_parquet(DATAFRAME_PATH, index=False)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "semvideo-hackathon-230523",
"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": "3.9.16"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|