image-classification timm

Model card for inception_v3.tv_in1k

A Inception-v3 image classification model. Trained on ImageNet-1k, torchvision weights.

Model Details

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('inception_v3.tv_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(
    'inception_v3.tv_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, 64, 147, 147])
    #  torch.Size([1, 192, 71, 71])
    #  torch.Size([1, 288, 35, 35])
    #  torch.Size([1, 768, 17, 17])
    #  torch.Size([1, 2048, 8, 8])

    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(
    'inception_v3.tv_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, 2048, 8, 8) shaped tensor

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

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

@article{DBLP:journals/corr/SzegedyVISW15,
  author    = {Christian Szegedy and
               Vincent Vanhoucke and
               Sergey Ioffe and
               Jonathon Shlens and
               Zbigniew Wojna},
  title     = {Rethinking the Inception Architecture for Computer Vision},
  journal   = {CoRR},
  volume    = {abs/1512.00567},
  year      = {2015},
  url       = {http://arxiv.org/abs/1512.00567},
  archivePrefix = {arXiv},
  eprint    = {1512.00567},
  timestamp = {Mon, 13 Aug 2018 16:49:07 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/SzegedyVISW15.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}