timm/convformer_s36.sail_in1k

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('convformer_s36.sail_in1k', pretrained=True)
model = model.eval()

# obtener transformaciones específicas del modelo (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 single image into batch of 1

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

Extracción de Mapas 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(
'convformer_s36.sail_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()

# obtener transformaciones específicas del modelo (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 single image into batch of 1

for o in output:
  print(o.shape)

Embeebimientos 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(
'convformer_s36.sail_in1k',
pretrained=True,
num_classes=0,
)
model = model.eval()

# obtener transformaciones específicas del modelo (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))

# o equivalente (sin necesidad de configurar num_classes=0)

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

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