Training on new data

[zabhishekgupta]

What's parameter to change to train the model on different data set than Minst etc..

[ndrplz]

Hi @zabhishekgupta ,
you can implement the loader for your dataset in data_load.py, then pass as argument the name of your new dataset in main.py with --dataset option

[zabhishekgupta]

thanks a lot Andrea.. in the model its not very clear where data is been split for training on clean and noise images... can you please help.

Regards,
Abhishek

[ndrplz]

For MNIST dataset this takes place here, which in turn calls this function to transform the images. This returns for each split a list of TransformingAutoencoderExample. Each TransformingAutoencoderExample in turn stores pre-trasform image (view_1), post-transform image (view_2) and transformation applied.
Hope this helps!