import torch model = torch.hub.load('XingangPan/IBN-Net', 'resnet50_ibn_a', pretrained=True) model.eval()
All pre-trained models expect input images normalized in the same way,
i.e. mini-batches of 3-channel RGB images of shape
(3 x H x W), where
W are expected to be at least
The images have to be loaded in to a range of
[0, 1] and then normalized using
mean = [0.485, 0.456, 0.406]
std = [0.229, 0.224, 0.225].
Here’s a sample execution.
# Download an example image from the pytorch website import urllib url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg") try: urllib.URLopener().retrieve(url, filename) except: urllib.request.urlretrieve(url, filename)
# sample execution (requires torchvision) from PIL import Image from torchvision import transforms input_image = Image.open(filename) preprocess = transforms.Compose([ transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), ]) input_tensor = preprocess(input_image) input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model # move the input and model to GPU for speed if available if torch.cuda.is_available(): input_batch = input_batch.to('cuda') model.to('cuda') with torch.no_grad(): output = model(input_batch) # Tensor of shape 1000, with confidence scores over Imagenet's 1000 classes print(output) # The output has unnormalized scores. To get probabilities, you can run a softmax on it. print(torch.nn.functional.softmax(output, dim=0))
IBN-Net is a CNN model with domain/appearance invariance. Motivated by style transfer works, IBN-Net carefully unifies instance normalization and batch normalization in a single deep network. It provides a simple way to increase both modeling and generalization capacities without adding model complexity. IBN-Net is especially suitable for cross domain or person/vehicle re-identification tasks.
The corresponding accuracies on ImageNet dataset with pretrained models are listed below.
|Model name||Top-1 acc||Top-5 acc|
The rank1/mAP on two Re-ID benchmarks Market1501 and DukeMTMC-reID are listed below (from michuanhaohao/reid-strong-baseline).
|ResNet50||94.5 (85.9)||86.4 (76.4)|
|ResNet101||94.5 (87.1)||87.6 (77.6)|
|SeResNet50||94.4 (86.3)||86.4 (76.5)|
|SeResNet101||94.6 (87.3)||87.5 (78.0)|
|SeResNeXt50||94.9 (87.6)||88.0 (78.3)|
|SeResNeXt101||95.0 (88.0)||88.4 (79.0)|
|ResNet50-IBN-a||95.0 (88.2)||90.1 (79.1)|