The predicted image is in almost null (all pixels are the same in grey)
bytemani opened this issue · comments
bytemani commented
Hi, everyone. I am tring to train the model on my own datasets and wanna know if everything is going well.
So, after few steps, I use the model like this:
"model = PConvUnet(vgg_weights=None, inference_only=True)
model.load(r"D:\projects_test\PConv-Keras-master\data\logs\myDataset_phase1\weights.01-7.00.h5", train_bn=False)"
and weights.01-7.00.h5 the midresult of the training.
However, it seems the prediction does not work well as the title depicted. Does anyone know what is going wrong or not? Thank you.
bytemani commented
solved.
Chayan Kumar Patodi commented
@bytemani how did you solve it ?!