---
title: mvitv2_huge_cls.fb_inw21k
canonical_url: "https://www.modelscope.cn/models/timm/mvitv2_huge_cls.fb_inw21k"
md_url: "https://www.modelscope.cn/models/timm/mvitv2_huge_cls.fb_inw21k.md"
repository: timm/mvitv2_huge_cls.fb_inw21k
last_updated: 2025-01-22
license: apache-2.0
pipeline_tag: image-classification
tasks:
  - image-classification
parameters: 694.8M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1828
stars: 0
tags:
  - image-classification
  - timm
  - transformers
---

# mvitv2_huge_cls.fb_inw21k

> mvitv2_huge_cls.fb_inw21k - timm 在 ModelScope 开源的模型。Model card for mvitv2hugecls.fbinw21k

timm/mvitv2_huge_cls.fb_inw21k 是 ModelScope 魔搭社区上的 694.8M 参数image-classification模型，采用 apache-2.0 许可。

- **Repository**: timm/mvitv2_huge_cls.fb_inw21k
- **License**: apache-2.0
- **Tasks**: image-classification
- **Parameters**: 694.8M
- **Tags**: image-classification, timm, transformers
- **Downloads**: 1828
- **Stars**: 0
- **Last updated**: 2025-01-22

Source: https://www.modelscope.cn/models/timm/mvitv2_huge_cls.fb_inw21k

---

# Model card for mvitv2_huge_cls.fb_inw21k

A MViT-v2 (multi-scale ViT) image classification model. Pretrained on ImageNet-22k (Winter21 variant) and fine-tuned on ImageNet-1k by paper authors. The classifier layout for this model was not shared and does not match expected lexicographical sorted synset order.

## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 694.8
  - GMACs: 120.7
  - Activations (M): 243.6
  - Image size: 224 x 224
- **Papers:**
  - MViTv2: Improved Multiscale Vision Transformers for Classification and Detection: https://arxiv.org/abs/2112.01526
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-22k
- **Original:** https://github.com/facebookresearch/mvit

## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('mvitv2_huge_cls.fb_inw21k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```

### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'mvitv2_huge_cls.fb_inw21k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 50, 1536) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
