README.md

---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for mvitv2_large_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): 234.6
  - GMACs: 42.2
  - Activations (M): 111.7
  - 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_large_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_large_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, 1152) shaped tensor

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