pip install timm

>>> import timm

>>> m = timm.create_model('mobilenetv3_large_100', pretrained=True)
>>> m.eval()

>>> import timm
>>> from pprint import pprint
>>> model_names = timm.list_models(pretrained=True)
>>> pprint(model_names)
[
    'adv_inception_v3',
    'cspdarknet53',
    'cspresnext50',
    'densenet121',
    'densenet161',
    'densenet169',
    'densenet201',
    'densenetblur121d',
    'dla34',
    'dla46_c',
]

>>> import timm
>>> from pprint import pprint
>>> model_names = timm.list_models('*resne*t*')
>>> pprint(model_names)
[
    'cspresnet50',
    'cspresnet50d',
    'cspresnet50w',
    'cspresnext50',
    ...
]

>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)

>>> import timm
>>> import torch
>>> x = torch.randn(1, 3, 224, 224)
>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True)
>>> features = model.forward_features(x)
>>> print(features.shape)
torch.Size([1, 960, 7, 7])

>>> timm.data.create_transform((3, 224, 224))
Compose(
    Resize(size=256, interpolation=bilinear, max_size=None, antialias=True)
    CenterCrop(size=(224, 224))
    MaybeToTensor()
    Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250]))
)

>>> model.pretrained_cfg
{'url': 'https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/mobilenetv3_large_100_ra-f55367f5.pth',
 'hf_hub_id': 'timm/mobilenetv3_large_100.ra_in1k',
 'architecture': 'mobilenetv3_large_100',
 'tag': 'ra_in1k',
 'custom_load': False,
 'input_size': (3, 224, 224),
 'fixed_input_size': False,
 'interpolation': 'bicubic',
 'crop_pct': 0.875,
 'crop_mode': 'center',
 'mean': (0.485, 0.456, 0.406),
 'std': (0.229, 0.224, 0.225),
 'num_classes': 1000,
 'pool_size': (7, 7),
 'first_conv': 'conv_stem',
 'classifier': 'classifier',
 'license': 'apache-2.0'}

>>> timm.data.resolve_model_data_config(model)
{'input_size': (3, 224, 224),
 'interpolation': 'bicubic',
 'mean': (0.485, 0.456, 0.406),
 'std': (0.229, 0.224, 0.225),
 'crop_pct': 0.875,
 'crop_mode': 'center'}

>>> data_cfg = timm.data.resolve_model_data_config(model)
>>> transform = timm.data.create_transform(**data_cfg)
>>> transform
Compose(
    Resize(size=256, interpolation=bicubic, max_size=None, antialias=True)
    CenterCrop(size=(224, 224))
    MaybeToTensor()
    Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250]))
)

>>> import requests
>>> from PIL import Image
>>> from io import BytesIO
>>> url = 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/timm/cat.jpg'
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> image

>>> model = timm.create_model('mobilenetv3_large_100', pretrained=True).eval()
>>> transform = timm.data.create_transform(
    **timm.data.resolve_model_data_config(model)
)

>>> image_tensor = transform(image)
>>> image_tensor.shape
torch.Size([3, 224, 224])

>>> output = model(image_tensor.unsqueeze(0))
>>> output.shape
torch.Size([1, 1000])

>>> probabilities = torch.nn.functional.softmax(output[0], dim=0)
>>> probabilities.shape
torch.Size([1000])

>>> values, indices = torch.topk(probabilities, 5)
>>> indices
tensor([281, 282, 285, 673, 670])

>>> IMAGENET_1k_URL = 'https://storage.googleapis.com/bit_models/ilsvrc2012_wordnet_lemmas.txt'
>>> IMAGENET_1k_LABELS = requests.get(IMAGENET_1k_URL).text.strip().split('\n')
>>> [{'label': IMAGENET_1k_LABELS[idx], 'value': val.item()} for val, idx in zip(values, indices)]
[{'label': 'tabby, tabby_cat', 'value': 0.5101025700569153},
 {'label': 'tiger_cat', 'value': 0.22490699589252472},
 {'label': 'Egyptian_cat', 'value': 0.1835290789604187},
 {'label': 'mouse, computer_mouse', 'value': 0.006752475164830685},
 {'label': 'motor_scooter, scooter', 'value': 0.004942195490002632}]