TIM
Codebase for the paper: "TIM: A Time Interval Machine for Audio-Visual Action Recognition"
File Explorer
- nms_cpu.cpp
- evaluate_detection_json.py
- evaluate_detection_json_ek100.py
- format_predictions.py
- format_predictions_epic.py
- format_two_stream_predictions_epic.py
- nms.py
- setup.py
- __init__.py
- extract_feats.py
- run_net.py
- test.py
- train.py
- __init__.py
- loader.py
- sliding_window.py
- drloc.py
- iou.py
- loss.py
- sigmoid.py
- __init__.py
- encodings.py
- head.py
- transformers.py
- __init__.py
- build.py
- tim.py
- __init__.py
- checkpoint.py
- distributed.py
- env.py
- logging.py
- meters.py
- metrics.py
- misc.py
- multiprocessing.py
- parser.py
- __init__.py
- README.md
- SLOWFAST_R50.yaml
- SLOWFAST_R50.yaml
- SLOWFAST_R50.yaml
- __init__.py
- custom_config.py
- defaults.py
- __init__.py
- audio_loader_aveperception.py
- audio_loader_epic.py
- audio_record.py
- ave.py
- ave_record.py
- build.py
- epicsounds.py
- epicsounds_record.py
- loader.py
- perception.py
- perception_record.py
- sparse_image_warp.py
- spec_augment.py
- utils.py
- __init__.py
- audio_model_builder.py
- batchnorm_helper.py
- build.py
- head_helper.py
- losses.py
- resnet_helper.py
- stem_helper.py
- __init__.py
- bn_helper.py
- checkpoint.py
- distributed.py
- logging.py
- meters.py
- metrics.py
- misc.py
- multiprocessing.py
- parser.py
- __init__.py
- run_net.py
- test_net.py
- extract_audio.py
- make_npyfiles.py
- README.md
- requirements.txt
- OMNIVORE_feature.yaml
- OMNIVORE_feature.yaml
- OMNIVORE_feature.yaml
- __init__.py
- defaults.py
- __init__.py
- autoaugment.py
- ave.py
- ave_record.py
- build.py
- decoder.py
- epickitchens.py
- epickitchens_record.py
- frame_loader.py
- loader.py
- perception.py
- perception_record.py
- transform.py
- utils.py
- video_record.py
- __init__.py
- build.py
- losses.py
- omnivore_model.py
- optimizer.py
- swin_transformer.py
- swin_utils.py
- video_model_builder.py
- __init__.py
- distributed.py
- logging.py
- lr_policy.py
- meters.py
- metrics.py
- misc.py
- multiprocessing.py
- __init__.py
- extract_features.py
- run_net.py
- extract_frames.py
- make_npyfiles.py
- make_npyfiles.py
- extract_frames.py
- make_npyfiles.py
- README.md
- requirements.txt
- datasets.py
- ek100.py
- engine_for_finetuning.py
- feature_extraction.py
- functional.py
- mae.py
- masking_generator.py
- modeling_finetune.py
- optim_factory.py
- rand_augment.py
- random_erasing.py
- README.md
- run_class_finetuning.py
- transforms.py
- utils.py
- video_transforms.py
- vits.py
- volume_transforms.py
- extract_frames.py
- make_framepickle.py
- make_videoinfo.py
- merge_features.py
- README.md
- __init__.py
- extract_feats.py
- run_net.py
- test.py
- train.py
- __init__.py
- loader.py
- sliding_window.py
- __init__.py
- drloc.py
- loss.py
- __init__.py
- encodings.py
- head.py
- pool.py
- transformers.py
- __init__.py
- build.py
- tim.py
- __init__.py
- checkpoint.py
- distributed.py
- env.py
- logging.py
- meters.py
- metrics.py
- misc.py
- mixup.py
- multiprocessing.py
- parser.py
- __init__.py
- README.md
- .gitignore
- environment.yml
- README.md
# Use via CDN
jsDelivrjsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.
Command Glossary
Commands referenced in this DOCs, explained below.
conda activate
View Details ▼
conda activate
Activate a conda environment.
See also: `conda deactivate`.
conda activate myenv
Activate an existing environment named `myenv`:
conda activate {{path/to/myenv}}
Activate an existing environment located at custom path:
conda activate --stack myenv
Stack `myenv` environment on top of a previous environment making libraries/commands/variables from both accessible:
conda env
View Details ▼
conda env
Manage conda environments.
conda env create {{[-f|--file]}} {{path/to/file}}
Create an environment from an environment file (YAML, TXT, etc.):
conda env remove {{[-n|--name]}} {{environment_name}}
Delete an environment and everything in it:
conda env update {{[-f|--file]}} {{path/to/file}} --prune
Update an environment based on an environment file: