Hello, thanks for your nice work! Can you tell me the source of vggmconv1 features use

Hi. If I remember correctly (was a while ago) I used <a href="https://github.com/Caden

Thanks a lot~ The would be useful for me. I really appreciate your help~</p

<a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/us

should be <a href="https://data.lip6.fr/cadene/pretrainedmodels/vggm-786f2434.pth"

<div class="snippet-clipboard-content notranslate position-relative overflow-auto" data-snippet-clip

About the pretrained model ResNetVGGm1 about pytracking HOT 8 CLOSED

visionml commented on September 7, 2024

About the pretrained model ResNetVGGm1

from pytracking.

Comments (8)

martin-danelljan commented on September 7, 2024

Hi. If I remember correctly (was a while ago) I used this model and then I made a script that re-normalizes the weights to fit the torchvision resnet input, and reorders the weights from BGR to RGB. I could probably find the script if you would have any use for it.

I ended up comparing the network with the output from MatConvNet VGG-m, and they were very similar.

from pytracking.

happyflyhot commented on September 7, 2024

Thanks a lot~
The script would be useful for me. I really appreciate your help~

from pytracking.

happyflyhot commented on September 7, 2024

@martin-danelljan Hi, may you share that transform script with me? I failed to re-normalizes the weights myself...

from pytracking.

martin-danelljan commented on September 7, 2024

Hey. Sorry for the delay. Here is the code that I used. You need to have this repo in your python path.

import os
import sys
import torch
import torchvision
import pretrainedmodels

env_path = os.path.join(os.path.dirname(__file__), '..')
if env_path not in sys.path:
    sys.path.append(env_path)


def main():
    resnet18 = torchvision.models.__dict__['resnet18'](pretrained=True)
    vggm = pretrainedmodels.models.vggm()

    resnet18.vggmconv1 = vggm.features[0]

    # Convert to RGB
    weight = resnet18.vggmconv1.weight.clone()
    resnet18.vggmconv1.weight[:,0,:,:] = weight[:,2,:,:]
    resnet18.vggmconv1.weight[:,2,:,:] = weight[:,0,:,:]

    # Normalize
    vgg_mean = torch.Tensor(vggm.mean[::-1])
    torch_std = torch.Tensor([0.229, 0.224, 0.225]).view(1,-1,1,1)
    resnet18.vggmconv1.weight[...] = resnet18.vggmconv1.weight * (torch_std*255)


    torch.save(resnet18.state_dict(), '../features/pretrained/resnet18_vggmconv1.pth')


if __name__ == '__main__':
    main()

from pytracking.

noobgrow commented on September 7, 2024

the model vggm is no longer aviable,could please send me one?
'vggm': {
'imagenet':
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/vggm-786f2434.pth',

from pytracking.

noobgrow commented on September 7, 2024

should be
https://data.lip6.fr/cadene/pretrainedmodels/vggm-786f2434.pth

from pytracking.

noobgrow commented on September 7, 2024

    model = VGGM(num_classes=1000)
    checkpoint = torch.load('vggm-786f2434.pth')
    for key in list(checkpoint.keys()):
        if 'classifier.' in key:
            checkpoint[key.replace('classifier.', 'classif.')] = checkpoint[key]
            del checkpoint[key]
    model.load_state_dict(checkpoint)

from pytracking.

noobgrow commented on September 7, 2024

    model = VGGM(num_classes=1000)
    checkpoint = torch.load('vggm-786f2434.pth')
    for key in list(checkpoint.keys()):
        if 'classifier.' in key:
            checkpoint[key.replace('classifier.', 'classif.')] = checkpoint[key]
            del checkpoint[key]
    model.load_state_dict(checkpoint)

from pytracking.

About the pretrained model ResNetVGGm1 about pytracking HOT 8 CLOSED

Comments (8)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent