Model card for test_efficientnet.r160_in1k

A very small test EfficientNet image classification model for testing and sanity checks. Trained on ImageNet-1k by Ross Wightman.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 0.4
  • GMACs: 0.1
  • Activations (M): 0.6
  • Image size: 160 x 160
• Dataset: ImageNet-1k
• Papers:
  • PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
• Original: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

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('test_efficientnet.r160_in1k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
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)

Feature Map Extraction

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(
    'test_efficientnet.r160_in1k',
    pretrained=True,
    features_only=True,
)
model = model.eval()

# get model specific transforms (normalization, resize)
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 shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 16, 80, 80])
    #  torch.Size([1, 24, 40, 40])
    #  torch.Size([1, 32, 20, 20])
    #  torch.Size([1, 48, 10, 10])
    #  torch.Size([1, 64, 5, 5])

    print(o.shape)

Image Embeddings

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(
    'test_efficientnet.r160_in1k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
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, 256, 5, 5) shaped tensor

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

Model Comparison

By Top-1

model	top1	top1_err	top5	top5_err	param_count	img_size	crop_pct
test_efficientnet.r160_in1k	47.156	52.844	71.726	28.274	0.36	192	1.0
test_byobnet.r160_in1k	46.698	53.302	71.674	28.326	0.46	192	1.0
test_efficientnet.r160_in1k	46.426	53.574	70.928	29.072	0.36	160	0.875
test_byobnet.r160_in1k	45.378	54.622	70.572	29.428	0.46	160	0.875
test_vit.r160_in1k	42.0	58.0	68.664	31.336	0.37	192	1.0
test_vit.r160_in1k	40.822	59.178	67.212	32.788	0.37	160	0.875

Citation

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}