timm/mobilenetv4_conv_blur_medium.e500_r224_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('mobilenetv4_conv_blur_medium.e500_r224_in1k', pretrained=True)
model = model.eval()

# obtener transformaciones específicas del modelo (normalización, redimensionamiento)
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(
'mobilenetv4_conv_blur_medium.e500_r224_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()

# obtener transformaciones específicas del modelo (normalización, redimensionamiento)
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)

Embeddings 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(
'mobilenetv4_conv_blur_medium.e500_r224_in1k',
pretrained=True,
num_classes=0, # eliminar clasificador nn.Linear
)
model = model.eval()

# obtener transformaciones específicas del modelo (normalización, redimensionamiento)
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 is (batch_size, num_features) shaped tensor

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

output = model.forward_features(transforms(img).unsqueeze(0))
# el output no está agrupado, es un tensor con forma (1, 960, 7, 7)

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