Regnety 640.seer

🚀 Model card for regnety_640.seer

A RegNetY-64GF feature / backbone model. Pretrained according to SEER: self-supervised learning with SwAV on "2B random internet images".

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

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

🚀 Quick Start

This README provides detailed information about the regnety_640.seer model, including its details, usage examples, and comparison with other models.

✨ Features

• Enhanced Implementation: The timm implementation of RegNet has several enhancements such as stochastic depth, gradient checkpointing, etc.
• Pretrained on Large Dataset: Pretrained on "2B random internet images" using the SEER method.

📚 Documentation

Model Details

💻 Usage Examples

Basic 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('regnety_640.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)

Advanced Usage - 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_640.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, 328, 56, 56])
    #  torch.Size([1, 984, 28, 28])
    #  torch.Size([1, 1968, 14, 14])
    #  torch.Size([1, 4920, 7, 7])

    print(o.shape)

Advanced Usage - 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_640.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, 4920, 7, 7) 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.

📄 License

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