Satya Allamraju

Hi @MLSlayer / anyothers , could you find any information on why the BN is omitted in 0'th iteration? Also, this same logic appears in the below forked code https://github.com/MLSlayer/Generative-Deep-Learning-Code-in-Pytorch/blob/49bd308a344f7c0710fbbb4004b726b372104959/models/GAN.py#L46

@daiyl - Just in case if you are still having this issue, the below are the steps how I created a work around: DATA_FOLDER = '/content/data_faces/img_align_celeba/' # assuming that you...

The log() applied to the predict tensor is creating issue with LabelSmoothing(). Hence I propose to use softmax_log() instead of log()

Hi jerett - we need the inputs of KLDivLoss to be in log space. Hence we need to apply log() - The -inf issue is because we have zeros in...