Downgrading to torchvision==0.13 worked for me

Just remove broken codes.

basenet/vgg16_bn.py

from torchvision import models
[-] from torchvision.models.vgg import model_urls < Remove Ln. 7

...

class vgg16_bn(torch.nn.Module):
    def __init__(self, pretrained=True, freeze=True):
        super(vgg16_bn, self).__init__()
[-]        model_urls['vgg16_bn'] = model_urls['vgg16_bn'].replace('https://', 'http://') < Remove Ln. 25

Downgrading to torchvision==0.13 worked for me

does not work bro

comment the "from torchvision.models.vgg import model_urls"
It worked here!

Insert all this:

all = [
'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn',
'vgg19_bn', 'vgg19',
]

model_urls = {
'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth',
'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth',
'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth',
'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth',
'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth',
'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth',
'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth',
'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth',
}

Or insert this for Resnet:

all = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152']

model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}

+1

comment the "from torchvision.models.vgg import model_urls" It worked here!

Insert all this:

all = [ 'VGG', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn', 'vgg19_bn', 'vgg19', ]

model_urls = { 'vgg11': 'https://download.pytorch.org/models/vgg11-bbd30ac9.pth', 'vgg13': 'https://download.pytorch.org/models/vgg13-c768596a.pth', 'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth', 'vgg19': 'https://download.pytorch.org/models/vgg19-dcbb9e9d.pth', 'vgg11_bn': 'https://download.pytorch.org/models/vgg11_bn-6002323d.pth', 'vgg13_bn': 'https://download.pytorch.org/models/vgg13_bn-abd245e5.pth', 'vgg16_bn': 'https://download.pytorch.org/models/vgg16_bn-6c64b313.pth', 'vgg19_bn': 'https://download.pytorch.org/models/vgg19_bn-c79401a0.pth', }

Or insert this for Resnet:

all = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152']

model_urls = { 'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth', 'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth', 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth', 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth', 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth', }

This worked for me. I had problem in the easyocr library that was using the vgg models. Made the changes that you mentioned in their modules.py and it worked. Thank you very much.

For current version of torchvision (0.16.2) the import should be:

from torchvision.models.vgg import VGG16_BN_Weights

but the code is not used anyway, so best to just remove it like mentioned:

Just remove broken codes.

basenet/vgg16_bn.py

from torchvision import models
[-] from torchvision.models.vgg import model_urls < Remove Ln. 7

...

class vgg16_bn(torch.nn.Module):
    def __init__(self, pretrained=True, freeze=True):
        super(vgg16_bn, self).__init__()
[-]        model_urls['vgg16_bn'] = model_urls['vgg16_bn'].replace('https://', 'http://') < Remove Ln. 25

Also, check this SO post.

I am facing the same issue. Is there a chance we can commit the fix in this repo?
It'd make the life easier.

I think there is a PR currently open:
#202
But tbh, I don't understand why bbox.py is also modified

rlrocha90

If you have proxy config didn't work :c