PyTorch Tutorials

Interested in getting started in a new CV area? Here are some tutorials to help get started.

Action Recognition

Pre-trained I3D Models on Kinetics400../build/examples_torch_action_recognition/demo_i3d_kinetics400.html

Recognize human actions in real-world videos with pre-trained I3D models

Finetuning SOTA Video Models on Your Dataset../build/examples_torch_action_recognition/finetune_custom.html

Hands on SOTA video models fine-tuning on your own dataset

Extracting video features from pre-trained models../build/examples_torch_action_recognition/extract_feat.html

Extracting video features from pre-trained models on your own videos

Computing FLOPS, latency and fps of a model../build/examples_torch_action_recognition/speed.html

How to compute FLOPS, number of parameters, latency and fps of a video model

DistributedDataParallel (DDP) framework../build/examples_torch_action_recognition/ddp_pytorch.html

How to use our DistributedDataParallel framework