Hamid Ali

In model file, you are using two functions [_make_layer ](https://github.com/XuJiacong/PIDNet/blob/f0ac91cdea7bf0cb2077b65e960c5b98b9173b0f/models/pidnet.py#L103 )and [_make_single_layer](https://github.com/XuJiacong/PIDNet/blob/f0ac91cdea7bf0cb2077b65e960c5b98b9173b0f/models/pidnet.py#L123). In both functions you are doing ``` downsample = nn.Sequential( nn.Conv2d(inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(planes...

Hi @divamgupta, thanks for your reply. New changes have been made in code to make it compatible with rest of the repo functionality. Please test it with cli tools. I...

Hi @stemper0123 Activation function after the batch normalization helps in preserving non-linearity, improves model convergence during gradient propagation, thus resulting in improved model performance and effective learning.

You can update display method with below code to show overlay Image. I have tested it in my [BASNET example](https://keras.io/examples/vision/basnet_segmentation/). Right before showing predicted segmentation map update the display method...

@Aziz-Prithibee13 There are three mistakes I noticed in code you shared. 1. In `load_paths` methods, its loading paths of only first 140 images and masks, that's why you are not...

Hi @Prithibee13 1. Batch size is not increasing because of low GPU memory. That's not a programming problem, either decrease your input image size or arrange a better GPU (you...