xcit_nano_12_p8_384.fb_dist_in1k

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('xcit_nano_12_p8_384.fb_dist_in1k', pretrained=True)
model = model.eval()

# obtain model specific transforms (normalización, cambio de tamaño)
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 una sola imagen en un lote de 1

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

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(
'xcit_nano_12_p8_384.fb_dist_in1k',
pretrained=True,
num_classes=0, # remover el clasificador nn.Linear
)
model = model.eval()

# obtain model specific transforms (normalización, cambio de tamaño)
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)) # el output es un tensor de tamaño (batch_size, num_features)

# o de manera equivalente (sin necesidad de establecer num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# el output no está agrupado, es un tensor de tamaño (1, 2305, 128)

output = model.forward_head(output, pre_logits=True)
# el output es un tensor de tamaño (1, num_features)