convnext_small.fb_in22k

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('convnext_small.fb_in22k', pretrained=True)
model = model.eval()

# obtener las 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)) # transformar imagen única en lote de 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('convnext_small.fb_in22k', pretrained=True, features_only=True)
model = model.eval()

# obtener las 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)) # transformar imagen única en lote de 1

for o in output:
# print shape of each feature map in output
# e.g.:
#  torch.Size([1, 96, 56, 56])
#  torch.Size([1, 192, 28, 28])
#  torch.Size([1, 384, 14, 14])
#  torch.Size([1, 768, 7, 7])

print(o.shape)

Incorporaciones 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('convnext_small.fb_in22k', pretrained=True, num_classes=0)
model = model.eval()

# obtener las 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)) # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 768, 7, 7) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor