convnextv2 nano.fcmae ft in22k in1k EU AI Act Compliance-Profil

Model card for convnextv2_nano.fcmae_ft_in22k_in1k

A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then ImageNet-1k.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 15.6
  • GMACs: 2.5
  • Activations (M): 8.4
  • Image size: train = 224 x 224, test = 288 x 288
• Papers:
  • ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders: https://arxiv.org/abs/2301.00808
• Original: https://github.com/facebookresearch/ConvNeXt-V2
• Dataset: ImageNet-1k
• Pretrain Dataset: ImageNet-1k

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('convnextv2_nano.fcmae_ft_in22k_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(
    'convnextv2_nano.fcmae_ft_in22k_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(

Ihre Pflichten als convnextv2 nano.fcmae ft in22k in1k-Betreiber

Ihren Fortschritt verfolgen

Registrieren Sie sich, um Verpflichtungen zu verfolgen, Fristbenachrichtigungen zu erhalten und Auditpakete zu erstellen.

Tags

Bibliothek