Model card for regnetz_040.ra3_in1k

A RegNetZ-4GF image classification model. Trained on ImageNet-1k by Ross Wightman in timm.

The timm RegNet implementation includes a number of enhancements not present in other implementations, including:

• stochastic depth
• gradient checkpointing
• layer-wise LR decay
• configurable output stride (dilation)
• configurable activation and norm layers
• option for a pre-activation bottleneck block used in RegNetV variant
• only known RegNetZ model definitions with pretrained weights

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 27.1
  • GMACs: 4.1
  • Activations (M): 24.2
  • Image size: train = 256 x 256, test = 320 x 320
• Papers:
  • Fast and Accurate Model Scaling: https://arxiv.org/abs/2103.06877
• Dataset: ImageNet-1k
• Original: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

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('regnetz_040.ra3_in1k', 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)

Feature Map Extraction

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(
    'regnetz_040.ra3_in1k',
    pretrained=True,
    features_only=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

for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 32, 128, 128])
    #  torch.Size([1, 48, 64, 64])
    #  torch.Size([1, 104, 32, 32])
    #  torch.Size([1, 240, 16, 16])
    #  torch.Size([1, 528, 8, 8])

    print(o.shape)

Image Embeddings

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(
    'regnetz_040.ra3_in1k',
    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, 528, 8, 8) shaped tensor

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

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

For the comparison summary below, the ra_in1k, ra3_in1k, ch_in1k, sw_*, and lion_* tagged weights are trained in timm.

Citation

@InProceedings{Dollar2021,
  title = {Fast and Accurate Model Scaling},
  author = {Piotr Doll{'a}r and Mannat Singh and Ross Girshick},
  booktitle = {CVPR},
  year = {2021}
}

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}