Meta tags:
description=A deep learning library for video understanding research;

Headings (most frequently used words):

video, pytorchvideo, deep, learning, library, for, understanding, research, based, on, pytorch, reproducible, model, zoo, efficient, components, get, started,

Text of the page (most frequently used words):
video (11), pytorchvideo (7), the (5), model (5), #components (4), for (3), load (3), transform (3), crop_size (3), clip_start_sec (3), video_data (3), preds (3), get (3), zoo (3), use (3), pytorch (3), instructions (2), torch (2), pretrained (2), compose (2), lambda (2), clip_duration (2), secs (2), all (2), inference (2), install (2), started (2), and (2), efficient (2), that (2), are (2), easy (2), github (2), tutorials (2), deep (2), learning (2), library (2), understanding (2), research (2), copyright, 2021, facebook, inc, legal, terms, privacy, detailed, refer, hub, encodedvideo, from_path, applytransformtokey, key, uniformtemporalsubsample, num_frames, normalizevideo, mean, std, shortsidescale, size, side_size, centercropvideo, get_clip, start_sec, end_sec, functional, softmax, pred_class_ids, topk, indices, generate, top, predictions, clip, 255, data, transforms, some_video, avi, true, slow_r50, facebookresearch, pre, trained, import, required, tutorial, try, classification, with, confirm, requirements, following, pip, here, focused, fast, supports, accelerated, hardware, variety, state, art, models, their, associated, benchmarks, ready, reproducible, built, using, makes, ecosystem, based, docs,

Text of the page (random words):
pytorchvideo a deep learning library for video understanding research pytorchvideo tutorials docs github a deep learning library for video understanding research get started tutorials github based on pytorch built using pytorch makes it easy to use all the pytorch ecosystem components reproducible model zoo variety of state of the art pretrained video models and their associated benchmarks that are ready to use efficient video components video focused fast and efficient components that are easy to use supports accelerated inference on hardware get started install pytorchvideo confirm requirements following the instructions here pip install pytorchvideo try video classification with model zoo for detailed instructions refer to the pytorchvideo model zoo inference tutorial import all the required components load pre trained model model torch hub load facebookresearch pytorchvideo slow_r50 pretrained true load video video encodedvideo from_path some_video avi compose video data transforms transform applytransformtokey key video transform compose uniformtemporalsubsample num_frames lambda lambda x x 255 0 normalizevideo mean std shortsidescale size side_size centercropvideo crop_size crop_size crop_size get clip clip_start_sec 0 0 secs clip_duration 2 0 secs video_data video get_clip start_sec clip_start_sec end_sec clip_start_sec clip_duration video_data transform video_data generate top 5 predictions preds torch nn functional softmax preds pred_class_ids preds topk k 5 indices pytorchvideo copyright 2021 facebook inc legal privacy terms