I can't download pretrained model

[anzheng13]

No description provided.

[anzheng13]

I download this in windows

[WENDGOUNDI]

Use this link
https://drive.google.com/file/d/19NWziHWh1LgCcHU34geoKwYezAogv9fX/view

[anzheng13]

Thank you.

[marsna]

Can you run inference.py with pretrained model?
I run inference.py and see error:
Traceback (most recent call last):
File "inference.py", line 78, in
main()
File "inference.py", line 32, in main
model.load_state_dict(checkpoint['state_dict'])
KeyError: 'state_dict'

[laisiewcheng]

Use this link
https://drive.google.com/file/d/19NWziHWh1LgCcHU34geoKwYezAogv9fX/view

May I know this is pretrained using what dataset? Sports1M?

[skyqwe123]

Can you run inference.py with pretrained model?
I run inference.py and see error:
Traceback (most recent call last):
File "inference.py", line 78, in
main()
File "inference.py", line 32, in main
model.load_state_dict(checkpoint['state_dict'])
KeyError: 'state_dict'

@marsna
I have a similar problem. Have you solved it

[marsna]

I didn't solve it in the end, even though I asked for help via email.

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "jfzhang95/pytorch-video-recognition" <[email protected]&gt;; 发送时间:&nbsp;2021年3月9日(星期二) 晚上9:13 收件人:&nbsp;"jfzhang95/pytorch-video-recognition"<[email protected]&gt;; 抄送:&nbsp;"Mars.Nan"<[email protected]&gt;;"Mention"<[email protected]&gt;; 主题:&nbsp;Re: [jfzhang95/pytorch-video-recognition] I can't download pretrained model (#44) Can you run inference.py with pretrained model? I run inference.py and see error: Traceback (most recent call last): File "inference.py", line 78, in main() File "inference.py", line 32, in main model.load_state_dict(checkpoint['state_dict']) KeyError: 'state_dict' @marsna I have a similar problem. Have you solved it — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[skyqwe123]

I didn't solve it in the end, even though I asked for help via email.
…
------------------ 原始邮件 ------------------ 发件人: "jfzhang95/pytorch-video-recognition" <[email protected]>; 发送时间: 2021年3月9日(星期二) 晚上9:13 收件人: "jfzhang95/pytorch-video-recognition"<[email protected]>; 抄送: "Mars.Nan"<[email protected]>;"Mention"<[email protected]>; 主题: Re: [jfzhang95/pytorch-video-recognition] I can't download pretrained model (#44) Can you run inference.py with pretrained model? I run inference.py and see error: Traceback (most recent call last): File "inference.py", line 78, in main() File "inference.py", line 32, in main model.load_state_dict(checkpoint['state_dict']) KeyError: 'state_dict' @marsna I have a similar problem. Have you solved it — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

@marsna I have solved it, change the code like this, it works for me：
model = C3D(num_classes=101, pretrained=True)
model.to(device)
model.eval()

[vsumm]

model = C3D(num_classes=101, pretrained=True)
model.to(device)
model.eval()

@skyqwe123

Thanks for giving an idea to resolve the state_dict error. you cant use C3D directly instead of use

    model = C3D_model.C3D(num_classes=101, pretrained=True)
    model.to(device)
    model.eval()

use this in inference.py

[farazBhatti]

No, it wont work as it will only load random weights. Pretrained model shared is trained on sport dataset with 487 classes