search

zhanglichao / generatedTIR_tracking

Synthetic data generation for end-to-end TIR tracking (TIP2018)
53 stars 12 forks source link

errors of using your pix2pix model #3

Open xingchenzhang opened 5 years ago

xingchenzhang commented 5 years ago

Hi,

Thank you for your very nice work!

I am now trying to test with your trained model using my RGB data to generate infrared data. But I got the following error:

"size mismatch for model.model.3.weight: copying a param with shape torch.Size([128, 1, 4, 4]) from checkpoint, the shape in current model is torch.Size([128, 3, 4, 4])."

do you have any idea why this happen and how to solve this?

Thanks a lot!

DereenMec commented 5 years ago

我也遇到了相同的问题，楼主最后是怎么解决的？

zhanglichao commented 4 years ago

Hi,

Sorry for the late check as these months busy with a submission. Hope you have solved it at early stage.

As I understand, the input/output of the channels number setting should be equivalent with that the checkpoint model.

I uploaded the 'opt.txt' when I normally used for generating TIR data. Maybe you can refer to it.

best, Lichao

makslevental commented 4 years ago

@zhanglichao

the opts file isn't correct. here are the model params generated from your opt

['model.model.0.weight',
 'model.model.1.model.1.weight',
 'model.model.1.model.2.weight',
 'model.model.1.model.2.bias',
 'model.model.1.model.2.running_mean',
 'model.model.1.model.2.running_var',
 'model.model.1.model.2.num_batches_tracked',
 'model.model.1.model.3.model.1.weight',
 'model.model.1.model.3.model.2.weight',
 'model.model.1.model.3.model.2.bias',
 'model.model.1.model.3.model.2.running_mean',
 'model.model.1.model.3.model.2.running_var',
 'model.model.1.model.3.model.2.num_batches_tracked',
 'model.model.1.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.2.num_batches_tracked',
 'model.model.1.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.3.model.2.num_batches_tracked',
 'model.model.1.model.3.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.num_batches_tracked',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.num_batches_tracked',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.3.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.num_batches_tracked',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.num_batches_tracked',
 'model.model.1.model.3.model.3.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.num_batches_tracked',
 'model.model.1.model.3.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.3.model.3.model.6.num_batches_tracked',
 'model.model.1.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.3.model.6.num_batches_tracked',
 'model.model.1.model.3.model.5.weight',
 'model.model.1.model.3.model.6.weight',
 'model.model.1.model.3.model.6.bias',
 'model.model.1.model.3.model.6.running_mean',
 'model.model.1.model.3.model.6.running_var',
 'model.model.1.model.3.model.6.num_batches_tracked',
 'model.model.1.model.5.weight',
 'model.model.1.model.6.weight',
 'model.model.1.model.6.bias',
 'model.model.1.model.6.running_mean',
 'model.model.1.model.6.running_var',
 'model.model.1.model.6.num_batches_tracked',
 'model.model.3.weight',
 'model.model.3.bias']

here are the model params in your checkpoint

['model.model.0.weight',
 'model.model.1.model.1.weight',
 'model.model.1.model.2.weight',
 'model.model.1.model.2.bias',
 'model.model.1.model.2.running_mean',
 'model.model.1.model.2.running_var',
 'model.model.1.model.3.model.1.weight',
 'model.model.1.model.3.model.2.weight',
 'model.model.1.model.3.model.2.bias',
 'model.model.1.model.3.model.2.running_mean',
 'model.model.1.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.1.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.3.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.3.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.3.model.5.weight',
 'model.model.1.model.3.model.3.model.6.weight',
 'model.model.1.model.3.model.3.model.6.bias',
 'model.model.1.model.3.model.3.model.6.running_mean',
 'model.model.1.model.3.model.3.model.6.running_var',
 'model.model.1.model.3.model.5.weight',
 'model.model.1.model.3.model.6.weight',
 'model.model.1.model.3.model.6.bias',
 'model.model.1.model.3.model.6.running_mean',
 'model.model.1.model.3.model.6.running_var',
 'model.model.1.model.5.weight',
 'model.model.1.model.6.weight',
 'model.model.1.model.6.bias',
 'model.model.1.model.6.running_mean',
 'model.model.1.model.6.running_var',
 'model.model.3.weight',
 'model.model.3.bias']

edit: ah i guess the only difference is num_batches_tracked which must be some sort of difference in how batch norm was implemented when you trained

zhanglichao commented 4 years ago

This can be fixed by renaming the parameters in the model dictionary.

Get Outlook for iOShttps://aka.ms/o0ukef

From: Maksim Levental notifications@github.com Sent: Wednesday, October 2, 2019 12:39:01 AM To: zhanglichao/generatedTIR_tracking generatedTIR_tracking@noreply.github.com Cc: Lichao zhanglichao@outlook.com; Mention mention@noreply.github.com Subject: Re: [zhanglichao/generatedTIR_tracking] errors of using your pix2pix model (#3)

@zhanglichaohttps://github.com/zhanglichao

the opts file isn't correct. here are the model params generated from your opt

['model.model.0.weight', 'model.model.1.model.1.weight', 'model.model.1.model.2.weight', 'model.model.1.model.2.bias', 'model.model.1.model.2.running_mean', 'model.model.1.model.2.running_var', 'model.model.1.model.2.num_batches_tracked', 'model.model.1.model.3.model.1.weight', 'model.model.1.model.3.model.2.weight', 'model.model.1.model.3.model.2.bias', 'model.model.1.model.3.model.2.running_mean', 'model.model.1.model.3.model.2.running_var', 'model.model.1.model.3.model.2.num_batches_tracked', 'model.model.1.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.2.num_batches_tracked', 'model.model.1.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.3.model.2.num_batches_tracked', 'model.model.1.model.3.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.2.num_batches_tracked', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.num_batches_tracked', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.3.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.num_batches_tracked', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.num_batches_tracked', 'model.model.1.model.3.model.3.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.6.num_batches_tracked', 'model.model.1.model.3.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.3.model.3.model.6.num_batches_tracked', 'model.model.1.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.3.model.6.num_batches_tracked', 'model.model.1.model.3.model.5.weight', 'model.model.1.model.3.model.6.weight', 'model.model.1.model.3.model.6.bias', 'model.model.1.model.3.model.6.running_mean', 'model.model.1.model.3.model.6.running_var', 'model.model.1.model.3.model.6.num_batches_tracked', 'model.model.1.model.5.weight', 'model.model.1.model.6.weight', 'model.model.1.model.6.bias', 'model.model.1.model.6.running_mean', 'model.model.1.model.6.running_var', 'model.model.1.model.6.num_batches_tracked', 'model.model.3.weight', 'model.model.3.bias']

here are the model params in your checkpoint

['model.model.0.weight', 'model.model.1.model.1.weight', 'model.model.1.model.2.weight', 'model.model.1.model.2.bias', 'model.model.1.model.2.running_mean', 'model.model.1.model.2.running_var', 'model.model.1.model.3.model.1.weight', 'model.model.1.model.3.model.2.weight', 'model.model.1.model.3.model.2.bias', 'model.model.1.model.3.model.2.running_mean', 'model.model.1.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.2.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.1.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.3.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.3.model.4.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.3.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.3.model.5.weight', 'model.model.1.model.3.model.3.model.6.weight', 'model.model.1.model.3.model.3.model.6.bias', 'model.model.1.model.3.model.3.model.6.running_mean', 'model.model.1.model.3.model.3.model.6.running_var', 'model.model.1.model.3.model.5.weight', 'model.model.1.model.3.model.6.weight', 'model.model.1.model.3.model.6.bias', 'model.model.1.model.3.model.6.running_mean', 'model.model.1.model.3.model.6.running_var', 'model.model.1.model.5.weight', 'model.model.1.model.6.weight', 'model.model.1.model.6.bias', 'model.model.1.model.6.running_mean', 'model.model.1.model.6.running_var', 'model.model.3.weight', 'model.model.3.bias']

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHubhttps://github.com/zhanglichao/generatedTIR_tracking/issues/3?email_source=notifications&email_token=AESN2YDMRZX6T6P5JRASTGTQMNVJLA5CNFSM4HGREJ2KYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEABXBAQ#issuecomment-537096322, or mute the threadhttps://github.com/notifications/unsubscribe-auth/AESN2YFW2EV5CXBG7X3YUHDQMNVJLANCNFSM4HGREJ2A.

zhanglichao commented 3 years ago

hi,

In the line 59 of the GAN_code/models/base_model.py, change 'model_fix' to model0.