Aller au contenu
ModelPrésentéExterne
Browse files

TimesFormerRefineOnHMDB51

This model is a fine-tuned version of TimeSformer (Time-Space Transformer) for video action recognition, trained on the HMDB51 dataset.

Sourcehuggingface.co/sumit7488/TimesFormerRefineOnHMDB51/tree/a5ecf612054805eb4a3878012a5c70c65156df35
TypeOtherVersionRevision a5ecf61BClasse

Source du modèle

Type
Other
Taille du fichier
464 MB
Version
vRevision a5ecf61
Mis à jour
24 oct. 2026
Téléchargements
5
Source
Hugging Face

Description de la source

🎬 TimeSformer Fine-Tuned on HMDB51

This model is a fine-tuned version of TimeSformer (Time-Space Transformer) for video action recognition, trained on the HMDB51 dataset.

📌 Model Overview

  • Architecture: TimeSformer (Transformer-based video model)
  • Task: Video Classification / Action Recognition
  • Dataset: HMDB51 (51 human action classes)
  • Framework: PyTorch + Hugging Face Transformers
  • Training Device: CUDA (GPU)

This model learns spatial and temporal features from video frames using transformer-based attention mechanisms.

📊 Training Details

  • Epochs: 15
  • Training Strategy:
    • Mixed Precision Training (torch.cuda.amp)
    • Early stopping based on validation performance
    • Best model checkpoint saved during training

📈 Training Results

EpochTrain LossTrain AccuracyVal LossVal Accuracy
13.93140.03233.78000.1248
23.58920.19763.25300.4353
33.02350.43542.65670.5340
42.57200.52462.23470.6033
52.28360.60092.01350.6327
62.08970.64191.86590.6536
71.96780.68071.80170.6667
81.88470.70301.77050.6627
91.82130.72371.73550.6627
101.75760.74141.73400.6680
111.70980.75491.72340.6765

✅ Best Validation Accuracy: 67.65%

  • Achieved at Epoch 11
  • Model checkpoint saved automatically

🧠 Dataset

HMDB51 is a widely used human action recognition dataset:

  • 51 action classes
  • Real-world videos
  • Diverse motion patterns and scenes

🚀 Usage

Install Dependencies

pip install torch torchvision transformers

Sources

1 source
Hugging FacePrincipalVersion a5ecf612054805eb4a3878012a5c70c65156df35
huggingface.co/sumit7488/TimesFormerRefineOnHMDB51/tree/a5ecf612054805eb4a3878012a5c70c65156df35

Vérifié 24 oct.

Download files

Artefacts du modèle

2 artefacts

model.safetensors

safetensors · 464 MB · SHA-256 0eda7112b140…177c · Hugging Face

Download file

pytorch_model.bin

bin · 464 MB · SHA-256 6861b3206cd7…2d67 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme6 aoûthuggingface.co/sumit7488/TimesFormerRefineOnHMDB51

--- license: mit tags: - video-classification - timesformer - action-recognition - hmdb51 - pytorch datasets: - hmdb51 --- # 🎬 TimeSformer Fine-Tuned on HMDB51 This model is a fine-tuned version of **TimeSformer (Time-Space Transformer)** for **video action recognition**, trained on the **HMDB51 dataset**. --- ## 📌 Model Overview - **Architecture:** TimeSformer (Transformer-based video model) - **Task:** Video Classification / Action Recognition - **Dataset:** HMDB51 (51 human action classes) - **Framework:** PyTorch + Hugging Face Transformers - **Training Device:** CUDA (GPU) This model learns spatial and temporal features from video frames using transformer-based attention mechanisms. --- ## 📊 Training Details - **Epochs:** 15 - **Training Strategy:** - Mixed Precision Training (`torch.cuda.amp`) - Early stopping based on validation performance - Best model checkpoint saved during training --- ## 📈 Training Results | Epoch | Train Loss | Train Accuracy | Val Loss | Val Accuracy | |------|------------|----------------|----------|--------------| | 1 | 3.9314 | 0.0323 | 3.7800 | 0.1248 | | 2 | 3.5892 | 0.1976 | 3.2530 | 0.4353 | | 3 | 3.0235 | 0.4354 | 2.6567 | 0.5340 | | 4 | 2.5720 | 0.5246 | 2.2347 | 0.6033 | | 5 | 2.2836 | 0.6009 | 2.0135 | 0.6327 | | 6 | 2.0897 | 0.6419 | 1.8659 | 0.6536 | | 7 | 1.9678 | 0.6807 | 1.8017 | 0.6667 | | 8 | 1.8847 | 0.7030 | 1.7705 | 0.6627 | | 9 | 1.8213 | 0.7237 | 1.7355 | 0.6627 | | 10 | 1.7576 | 0.7414 | 1.7340 | 0.6680 | | 11 | 1.7098 | 0.7549 | 1.7234 | 0.6765 | ### ✅ Best Validation Accuracy: **67.65%** - Achieved at **Epoch 11** - Model checkpoint saved automatically --- ## 🧠 Dataset **HMDB51** is a widely used human action recognition dataset: - 51 action classes - Real-world videos - Diverse motion patterns and scenes --- ## 🚀 Usage ### Install Dependencies ```bash pip install torch torchvision transformers

Note24 oct.huggingface.co/sumit7488/TimesFormerRefineOnHMDB51

Source context: 5 downloads · 0 likes · Pipeline video-classification · Repo sumit7488/TimesFormerRefineOnHMDB51

Note6 aoûthuggingface.co/sumit7488/TimesFormerRefineOnHMDB51

Source context: 4 downloads · 0 likes · Pipeline video-classification · Repo sumit7488/TimesFormerRefineOnHMDB51