samvit base patch16.sa1b EU AI Act Compliance Profile

Model card for samvit_base_patch16.sa1b

A Segment-Anything Vision Transformer (SAM ViT) image feature model (NOTE: for features and fine-tune, segmentation head not included). Pretrained on SA-1B for segementation by paper authors w/ initialization from MAE weights.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 89.7
  • GMACs: 486.4
  • Activations (M): 1343.3
  • Image size: 1024 x 1024
• Papers:
  • Segment Anything: https://arxiv.org/abs/2304.02643
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
• Original: https://github.com/facebookresearch/segment-anything
• Pretrain Dataset: SA-1B

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('samvit_base_patch16.sa1b', 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

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(
    'samvit_base_patch16.sa1b',
    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_tr

Your obligations as a samvit base patch16.sa1b deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library