batch_renorm exists some errors

[Rebeccayoyo]

TypeError: add_weight() got multiple values for argument 'name'
this is about the version of tensorflow or keras?

[hellloxiaotian]

The codes are right. Please check your environment with that of this paper.

[youngyuzheng]

TypeError: add_weight() got multiple values for argument 'name'
Have you ever figured out how to solve this error?

[hellloxiaotian]

The codes are right. Please check your environment with that of this paper.

[ouisyasser]

I have also the same error ? have someone ever figured out how to solve the problem ?

[hellloxiaotian]

I have run the code again. However, I didn't find the question above.

[hellloxiaotian]

My running environment of BRDNet is as follows,
Tensorflow 1.3.0
Keras 2.0
Numpy
Opencv 2
Python 2.7
Cuda 8.0
Cudnn 7.5
Ubuntu 14.04

[ouisyasser]

Hello Can you please provide the right code to denoise images ? I have a PNG images file and I want to denoise it using your code. Thank you Le mer. 24 juin 2020 à 5:40 AM, Chunwei Tian <[email protected]> a écrit :

…

My running environment of BRDNet is as follows, NvidiaCUDAof8.0andcuDNNof7.5a NvidiNvidiaCUDAof8.0andcuDNNof7.5aaCUDAof8.0andcuDNNof7.5a Tensorflow 1.3.0 Keras 2.0 Numpy Opencv 2 Python 2.7 Cudnn 8.0 Cuda 7.5 Ubuntu 14.04 — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#4 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AOAXXX55FO4XKNMGYEVH253RYF7VPANCNFSM4LD7BLVA> .

[hellloxiaotian]

Dear Mr or Miss, I have run my code on my computer again, which can be successfully run on my computer. Best wishes, Chunwei Tian At 2020-06-24 22:33:59, "ouisyasser" <[email protected]> wrote: Hello Can you please provide the right code to denoise images ? I have a PNG images file and I want to denoise it using your code. Thank you Le mer. 24 juin 2020 à 5:40 AM, Chunwei Tian <[email protected]> a écrit :

My running environment of BRDNet is as follows, NvidiaCUDAof8.0andcuDNNof7.5a NvidiNvidiaCUDAof8.0andcuDNNof7.5aaCUDAof8.0andcuDNNof7.5a Tensorflow 1.3.0 Keras 2.0 Numpy Opencv 2 Python 2.7 Cudnn 8.0 Cuda 7.5 Ubuntu 14.04 — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#4 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AOAXXX55FO4XKNMGYEVH253RYF7VPANCNFSM4LD7BLVA> .

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[Rebeccayoyo]

I have also the same error ? have someone ever figured out how to solve the problem ?

当时是复查了环境依赖项，与原作者一致，这个问题就解决了

[HaowenGuan]

This problem can be solved by changing
self.gamma = self.add_weight(shape,initializer=self.gamma_init,regularizer=self.gamma_regularizer,name='{}_gamma'.format(self.name))
to
self.gamma = self.add_weight(shape=shape,initializer=self.gamma_init,regularizer=self.gamma_regularizer,name='{}_gamma'.format(self.name))
for all of add_weight call

[HaowenGuan]

It is really hard to match your original running enviroment, since tensorflow no longer support python version lower than 3.5
Can you guys fix the code to match the mainstream enviroment?
I am having problem to load_model, too.

[adnankhalid7454]

ValueError: Shape must be rank 1 but is rank 0 for 'batch_renormalization_3/Reshape_10' (op: 'Reshape') with input shapes: [1,1,1,64], [].

can you please resolve this error while loading the model

[saimayasmeen4]

Hi https://github.com/adnankhalid7454, can you please let me know either your code is running?