Regnety 1280.seer

🚀 RegNetY-1280 SEER Model

This is a RegNetY-128GF feature/backbone model. It's pretrained using SEER, a self - supervised learning method with SwAV on "2B random internet images".

SEER is licensed under the SEER license. Copyright (c) Meta Platforms, Inc. All Rights Reserved. The license is a non - commercial license with usage and distribution restrictions.

The timm implementation of RegNet includes several enhancements not found in other implementations, such as:

• 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 the RegNetV variant
• The only known RegNetZ model definitions with pretrained weights

✨ Features

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 637.4
  • GMACs: 127.7
  • Activations (M): 71.6
  • Image size: 224 x 224
• Papers:
  • Self - supervised Pretraining of Visual Features in the Wild: https://arxiv.org/abs/2103.01988v2
  • Designing Network Design Spaces: https://arxiv.org/abs/2003.13678
• Original: https://github.com/facebookresearch/vissl
• Pretrain Dataset: RandomInternetImages - 2B

📚 Documentation

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('regnety_1280.seer', 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(
    'regnety_1280.seer',
    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, 112, 112])
    #  torch.Size([1, 528, 56, 56])
    #  torch.Size([1, 1056, 28, 28])
    #  torch.Size([1, 2904, 14, 14])
    #  torch.Size([1, 7392, 7, 7])

    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(
    'regnety_1280.seer',
    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, 7392, 7, 7) shaped tensor

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

📄 License

SEER is licensed under the SEER license. Copyright (c) Meta Platforms, Inc. All Rights Reserved. The license is a non - commercial license with usage and distribution restrictions.

📊 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.