ModelListedExternal

Videomae v2 Base Hmdb51 Finetuned

This repository contains a fine-tuned PyTorch checkpoint exported from Kaggle for reuse and future fine-tuning.

Sourcehuggingface.co/Kiffaz11/Videomae_v2_base-hmdb51-finetuned/tree/3620fdba4c16c29c0d7eb1da9013f227f22c7839

KindOtherBase modelOpenGVLab/VideoMAEv2-BaseVersionBest videomaev2 base 51clsCgrade

Model source

Kind: Other
File size: 329 MB
Base model: OpenGVLab/VideoMAEv2-Base
Version: vBest videomaev2 base 51cls
Updated: Oct 24, 2026
Source: Hugging Face

Source description

VideoMAE-v2 (Base) — HMDB51 (51 classes) Fine-tuned Checkpoint

This repository contains a fine-tuned PyTorch checkpoint exported from Kaggle for reuse and future fine-tuning.

best_videomaev2_base_51cls.pt — raw checkpoint (torch.load)
checkpoint_meta.json — metadata (best epoch, best val accuracy, etc.)
training_results.csv — epoch-level train/val accuracy
label2id.json / id2label.json — label maps (if available)

Training results

Best validation accuracy: 0.8626 (epoch 10)

Epoch	Train Acc	Val Acc	Saved Best
1	0.2614	0.7125	✅
2	0.5320	0.8147	✅
3	0.6024	0.8275	✅
4	0.6108	0.8259
5	0.6350	0.8450	✅
6	0.6444	0.8530	✅
7	0.6387	0.8530
8	0.6328	0.8578	✅
9	0.6583	0.8610	✅
10	0.6664	0.8626	✅

Download & load

from huggingface_hub import hf_hub_download
import torch

repo_id = "Kiffaz11/Videomae_v2_base-hmdb51-finetuned"
ckpt_path = hf_hub_download(repo_id=repo_id, filename="best_videomaev2_base_51cls.pt")
ckpt = torch.load(ckpt_path, map_location="cpu")

Notes

This repo stores a raw PyTorch checkpoint (not necessarily a save_pretrained() Transformers folder).
Use the included metadata + label maps to reconstruct the training/inference code you used in Kaggle.

Sources

1 source

Hugging FacePrimaryVersion 3620fdba4c16c29c0d7eb1da9013f227f22c7839

huggingface.co/Kiffaz11/Videomae_v2_base-hmdb51-finetuned/tree/3620fdba4c16c29c0d7eb1da9013f227f22c7839

Verified Oct 24

Model artifacts

1 artifact

best_videomaev2_base_51cls.pt

pt · 329 MB · SHA-256 7976ec58a805…d28e · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeAug 6huggingface.co/Kiffaz11/Videomae_v2_base-hmdb51-finetuned

--- library_name: transformers tags: - video-classification - action-recognition - VideoMAE base_model: OpenGVLab/VideoMAEv2-Base --- # VideoMAE-v2 (Base) — HMDB51 (51 classes) Fine-tuned Checkpoint This repository contains a fine-tuned PyTorch checkpoint exported from Kaggle for **reuse and future fine-tuning**. ## Contents - **`best_videomaev2_base_51cls.pt`** — raw checkpoint (`torch.load`) - **`checkpoint_meta.json`** — metadata (best epoch, best val accuracy, etc.) - **`training_results.csv`** — epoch-level train/val accuracy - **`label2id.json` / `id2label.json`** — label maps (if available) ## Training results - Best validation accuracy: **0.8626** (epoch **10**) | Epoch | Train Acc | Val Acc | Saved Best | |---:|---:|---:|:---:| | 1 | 0.2614 | 0.7125 | ✅ | | 2 | 0.5320 | 0.8147 | ✅ | | 3 | 0.6024 | 0.8275 | ✅ | | 4 | 0.6108 | 0.8259 | | | 5 | 0.6350 | 0.8450 | ✅ | | 6 | 0.6444 | 0.8530 | ✅ | | 7 | 0.6387 | 0.8530 | | | 8 | 0.6328 | 0.8578 | ✅ | | 9 | 0.6583 | 0.8610 | ✅ | | 10 | 0.6664 | 0.8626 | ✅ | ## Download & load ```python from huggingface_hub import hf_hub_download import torch repo_id = "Kiffaz11/Videomae_v2_base-hmdb51-finetuned" ckpt_path = hf_hub_download(repo_id=repo_id, filename="best_videomaev2_base_51cls.pt") ckpt = torch.load(ckpt_path, map_location="cpu") ``` ## Notes - This repo stores a **raw PyTorch checkpoint** (not necessarily a `save_pretrained()` Transformers folder). - Use the included metadata + label maps to reconstruct the training/inference code you used in Kaggle.

NoteAug 6huggingface.co/Kiffaz11/Videomae_v2_base-hmdb51-finetuned

Source context: 0 downloads · 1 likes · Pipeline video-classification · Library transformers · Repo Kiffaz11/Videomae_v2_base-hmdb51-finetuned