Praveen Kumar Chandaliya

icon indicating a website link www.svnit.ac.in

icon company SVNIT, Surat icon location Surat, India icon location Assistant Professor, Department of AI Sardar Vallabhbhai National Institute of Technology, Surat, India

Results 7 comments of Praveen Kumar Chandaliya

evaluate function in training step will raise error : "float division by zero"

When you generate pairs.txt file in this file you have mixture of similar match and dissimilar match are present randomly. so at the time of batch formation both the type...

InvalidArgumentError: You must feed a value for placeholder tensor 'real_images' with dtype float and shape

check the place holde value or the size of image with batch[64,64,64,1]

PatchGAN?

In the case of PatchGAN, l**ast layer of Discriminator** have output channel always 1. nn.Conv2D(inchannel,outchannel,kernelsize,stride,padding): nn.Conv2D(128,**1**,3,1,1) ' '

Training failes with ModuleNotFoundError when using train_mn.py

Similar type error ModuleNotFoundError: No module named 'training.los s'

Why requirments.txt is empty

sudo apt update sudo apt install -y python3-dev python3-pip git pip3 install testresources pip3 install --upgrade pip setuptools requests sudo pip install -U virtualenv virtualenv -p python3 venv source venv/bin/activate...

Why is tanh not used as activation at the last layer of generator?

the last layer in the generator is tanh because it making value between -1 and 1. and make over the network is more stable in the case of color image...

Bigger batchsize?

If you increase the batch size than get memory overflow error on GPU