tynguyen/unsupervisedDeepHomographyRAL2018

Error in FineTuning the Model

nayeemiiitd opened this issue · 5 comments

After downloading the Pretrained model on synthetic dataset and storing it in models directory. I ran the homography_CNN_real.py script, but it gave the error as:

e1

I have done the preprocessing of my dataset using gen_real_data.py script. I was using l1_loss for finetuning the network.

I guess the issue come when you set --batch_norm to be True.

Can you try not using batchnorm? When I trained the network, using batchnorm is inferior I set it off.

I tried setting --use_batch_norm as False, but still the same error.

I have the same issue with nayeemiiitd.@nayeemiiitd

Hi there, this bug has been fixed!

Thanks

Excuse me, when i run the homography_CNN_synthetic.py
I had meet the error : TypeError: cannot create weak reference to 'builtin_function_or_method' object
Do you know how to solve this problem?