Aller au contenu
ModelPrésentéExterne
Télécharger

CSC 51073 EP Computer Vision Final Project

Model: TimeSformer-Base (Kinetics-400 pretrained) Frame sampling: even Data balancing: maxfull Unfrozen last layers: 6 Task: workout action classification (plank, push-up, squat, russian-twist)

Sourcehuggingface.co/MTomita/CSC_51073_EP-Computer-Vision-Final-Project/tree/675514193a4e0f34a41679208dd7599320430753
TypeOtherVersionTimesformer max full even 6CClasse

Source du modèle

Type
Other
Taille du fichier
463 MB
Version
vTimesformer max full even 6
Mis à jour
24 oct. 2026
Source
Hugging Face

Description de la source

TimeSformer fine-tuned model

Checkpoint: timesformer_max_full_even_6.pt

Training configuration

  • Model: TimeSformer-Base (Kinetics-400 pretrained)
  • Frame sampling: even
  • Data balancing: max_full
  • Unfrozen last layers: 6
  • Task: workout action classification (plank, push-up, squat, russian-twist)

Notes

This repository provides a raw PyTorch checkpoint. To use it, load the checkpoint into a TimesformerForVideoClassification model with the same configuration used during training.

Sources

1 source
Hugging FacePrincipalVersion 675514193a4e0f34a41679208dd7599320430753
huggingface.co/MTomita/CSC_51073_EP-Computer-Vision-Final-Project/tree/675514193a4e0f34a41679208dd7599320430753

Vérifié 24 oct.

Artefacts du modèle

1 artefact

timesformer_max_full_even_6.pt

pt · 463 MB · SHA-256 2463bf3793ea…d6c0 · Hugging Face

Download file

Extraits de sources

2 extraits
Readme6 aoûthuggingface.co/MTomita/CSC_51073_EP-Computer-Vision-Final-Project

--- license: apache-2.0 tags: - video-classification - timesformer library_name: transformers --- # TimeSformer fine-tuned model **Checkpoint:** `timesformer_max_full_even_6.pt` ## Training configuration - Model: TimeSformer-Base (Kinetics-400 pretrained) - Frame sampling: even - Data balancing: max_full - Unfrozen last layers: 6 - Task: workout action classification (plank, push-up, squat, russian-twist) ## Notes This repository provides a raw PyTorch checkpoint. To use it, load the checkpoint into a `TimesformerForVideoClassification` model with the same configuration used during training.

Note6 aoûthuggingface.co/MTomita/CSC_51073_EP-Computer-Vision-Final-Project

Source context: 0 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo MTomita/CSC_51073_EP-Computer-Vision-Final-Project