mojoee
The frontend is just to extract the features from the image. The model itself will give the prediction by feeding in those extracted features
well that's fine, but makes it complicated because you need to make sure to transform your tensor from keras to the tensorflow format. I would say, it's better to stay...
i am also having issues training the Network with my own dataset at the moment. I have tried the usual things, as e.g. adjusting learning rate, optimizer, crop size, batch-size...
download the github, then arrange CamVid dataset or your own dataset in the folder structure mentioned. Then you can run the train.py method to train your own model. You can...
Did you get further on this matter? I also cannot find any test file
How is the blender solution going? Can you share?
So is there a possibility to only use the pointcloud without images?
replacing the parfor with a simple for loop solved the problem of crashing, but the script execution time was really slow
as the error says, you are running out of memory, which comes from the fact that your images in your custom training dataset is bigger than the images provided in...
has this issue been completed?