New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

why i got same number with Alexnet ? #1169

Open

Dushuai12138 opened this issue Nov 11, 2022 · 1 comment

Dushuai12138 commented Nov 11, 2022

please tell me some possible reason, thanks a lot

Author

Dushuai12138 commented Nov 11, 2022

model_name = 'inceptionresnetv2'  # could be fbresnet152 or inceptionresnetv2
model = pretrainedmodels.__dict__[model_name](num_classes=1001, pretrained=None)
model_to_load = torch.load(root + "model_file/inceptionresnetv2-520b38e4.pth")  # 注意修改
model.load_state_dict(model_to_load, strict=True)
model.last_linear = nn.Linear(1536, 6 * 101)

it is the previous codes, it can run well. but when i replace them with

model_name = 'Alexnet'  # could be fbresnet152 or inceptionresnetv2
model = models.alexnet(pretrained=True)
num_fc = model.classifier[6].in_features
model.classifier[6] = torch.nn.Linear(in_features=num_fc, out_features=606)

i got a result which has the same number

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment