convnextv2_large.fcmae_ft_in22k_in1k_384

Clasificación de imágenes

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_large.fcmae_ft_in22k_in1k_384', pretrained=True)
model = model.eval()

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))
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Extracción del mapa de características

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_large.fcmae_ft_in22k_in1k_384', pretrained=True, features_only=True)
model = model.eval()

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))

for o in output:
    print(o.shape)

Embeddings de imagen

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_large.fcmae_ft_in22k_in1k_384', pretrained=True, num_classes=0)
model = model.eval()

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 = model.forward_features(transforms(img).unsqueeze(0))

output = model.forward_head(output, pre_logits=True)