abdullah-abuolaim / multi-task-defocus-deblurring-dual-pixel-nimat Goto Github PK

Hi, I am very excited about the resulting effects and wondering when will you release the code and pre-trained model.

Hi! Thank you for the great work. May I ask if there are any plans to release the dataset?

hi,when I am according to the process ,configured the environment,while use the mdp_phase_1_wacv.hdf5 as the pretrained model,when training finished,I just get the PSNR=24.64 ,the parameter I changed 'ing_mini_b' from 8 to 6,because of the memory limited.The other parameters I didn't change.The dataset I choose is DPDD dataset，350 pairs images as the training dataset.the GPU is 2 NVIDIA 1080Ti.I don't know why

I download the dataset and find that 'train/c' includes blurred images? So, is the dataset building with an unsupervised way?

Invalid argument: ValueError: could not broadcast input array from shape (512,500,3) int$
shape (512,512,3)
Traceback (most recent call last):

File "/home/user/lib_local/miniconda3/lib/python3.8/site-packages/tensorflow/python/ops/script_ops.py", line 249, in call
ret = func(*args)

File "/home/user/lib_local/miniconda3/lib/python3.8/site-packages/tensorflow/python/autograph/impl/api.py", line 645, in wrapper
return func(*args, **kwargs)

File "/home/user/lib_local/miniconda3/lib/python3.8/site-packages/tensorflow/python/data/ops/dataset_ops.py", line 892, in generator_py_func
values = next(generator_state.get_iterator(iterator_id))

File "/home/user/lib_local/miniconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 839, in wrapped_generator
for data in generator_fn():

File "/data/user/liaozk/multi-task-defocus-deblurring-dual-pixel-nimat-main/mdp_code/data.py", line 205, in generator
src_ims[i] = img_src_c[s_p[0]:e_p[0],s_p[1]:e_p[1],:]

ValueError: could not broadcast input array from shape (512,500,3) into shape (512,512,3)

Thank you for your contribution. Have you ever meet this bug in the training phase 1? Thank you