Created
August 30, 2023 00:36
-
-
Save e96031413/b05bbde01c3ab1e3b22757584f5a51c7 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
RetinaNet model with the MobileNetV3 backbone from | |
Torchvision classification models. | |
Reference: https://github.com/pytorch/vision/blob/main/torchvision/models/detection/retinanet.py#L377-L405 | |
""" | |
import torchvision | |
import torch | |
from torchvision.models.detection import RetinaNet | |
from torchvision.models.detection.anchor_utils import AnchorGenerator | |
from thop import profile | |
def create_model(num_classes=4, pretrained=True, coco_model=False): | |
# Load the pretrained MobileNetV3 large features. | |
# TOP-1 ACC: 75.274, TOP-5 ACC: 92.566, Params: 5.5M, GFLOPs: 0.22G | |
backbone = torchvision.models.mobilenet_v3_large(weights='IMAGENET1K_V2').features | |
# backbone = torch.nn.Sequential(*(list(torchvision.models.resnet18(weights='IMAGENET1K_V1').children())[:-1])) | |
# We need the output channels of the last convolutional layers from the features for the RetinaNet model. | |
backbone.out_channels = 960 | |
# Generate anchors using the RPN. Here, we are using 5x3 anchors. | |
# Meaning, anchors with 5 different sizes and 3 different aspect | |
# ratios. | |
anchor_generator = AnchorGenerator( | |
sizes=((32, 64, 128, 256, 512),), | |
aspect_ratios=((0.5, 1.0, 2.0),) | |
) | |
# Final RetinaNet model. | |
model = RetinaNet( | |
backbone=backbone, | |
num_classes=num_classes, | |
anchor_generator=anchor_generator, | |
) | |
return model | |
if __name__ == '__main__': | |
input = torch.randn(1, 3, 640, 640).cuda() | |
target = {"boxes": torch.tensor([[100, 150, 300, 400]]).cuda(),"labels": torch.tensor([1]).cuda(),} | |
model = create_model(num_classes=3, pretrained=True, coco_model=False) | |
model = model.cuda() | |
""" | |
model.train() | |
out=model(input,[target]) | |
{'classification': tensor(1.0960, device='cuda:0', grad_fn=<DivBackward0>), | |
'bbox_regression': tensor(0.8155, device='cuda:0', grad_fn=<DivBackward0>)} | |
model.eval() | |
out=model(input) | |
[{'boxes': tensor([], device='cuda:0', size=(0, 4), grad_fn=<StackBackward0>), | |
'scores': tensor([], device='cuda:0', grad_fn=<IndexBackward0>), | |
'labels': tensor([], device='cuda:0', dtype=torch.int64)}] | |
""" | |
macs, params = profile(model, inputs=(input, )) | |
print('MACs = ' + str(macs/1000**3) + 'G') | |
print('Params = ' + str(params/1000**2) + 'M') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment