Views
No views yet
il-common dataset.1import birder
2from birder.inference.classification import infer_image
3
4(net, model_info) = birder.load_pretrained_model("vit_reg4_b16_mim-intermediate-il-common", inference=True)
5
6# Get the image size the model was trained on
7size = birder.get_size_from_signature(model_info.signature)
8
9# Create an inference transform
10transform = birder.classification_transform(size, model_info.rgb_stats)
11
12image = "path/to/image.jpeg" # or a PIL image, must be loaded in RGB format
13(out, _) = infer_image(net, image, transform)
14# out is a NumPy array with shape of (1, 371), representing class probabilities.1import birder
2from birder.inference.classification import infer_image
3
4(net, model_info) = birder.load_pretrained_model("vit_reg4_b16_mim-intermediate-il-common", inference=True)
5
6# Get the image size the model was trained on
7size = birder.get_size_from_signature(model_info.signature)
8
9# Create an inference transform
10transform = birder.classification_transform(size, model_info.rgb_stats)
11
12image = "path/to/image.jpeg" # or a PIL image
13(out, embedding) = infer_image(net, image, transform, return_embedding=True)
14# embedding is a NumPy array with shape of (1, 768)1@misc{dosovitskiy2021imageworth16x16words,
2 title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
3 author={Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby},
4 year={2021},
5 eprint={2010.11929},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2010.11929},
9}
10
11@misc{darcet2024visiontransformersneedregisters,
12 title={Vision Transformers Need Registers},
13 author={Timothée Darcet and Maxime Oquab and Julien Mairal and Piotr Bojanowski},
14 year={2024},
15 eprint={2309.16588},
16 archivePrefix={arXiv},
17 primaryClass={cs.CV},
18 url={https://arxiv.org/abs/2309.16588},
19}
20
21@misc{he2021maskedautoencodersscalablevision,
22 title={Masked Autoencoders Are Scalable Vision Learners},
23 author={Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Dollár and Ross Girshick},
24 year={2021},
25 eprint={2111.06377},
26 archivePrefix={arXiv},
27 primaryClass={cs.CV},
28 url={https://arxiv.org/abs/2111.06377},
29}