val-iisc/deligan
This project is an implementation of the Generative Adversarial Network proposed in our CVPR 2017 paper - DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data. DeLiGAN is a simple but effective modification of the GAN framework and aims to improve performance on datasets which are diverse yet small in size.
PythonMIT
Issues
- 0
how to use cpu to train for deli_gan
#9 opened by txb12345 - 5
Latent Space
#8 opened by Bob-RUC - 0
TypeError: ('An update must have the same type as the original shared variable (shared_var=W, shared_var.type=GpuArrayType<None>(float32, (False, True, False, False)), update_val=Elemwise{sub,no_inplace}.0, update_val.type=TensorType(float32, 4D)).', 'If the difference is related to the broadcast pattern, you can call the tensor.unbroadcast(var, axis_to_unbroadcast[, ...]) function to remove broadcastable dimensions.')
#7 opened by bluseking - 1
Some questions about the project
#2 opened by OwalnutO - 2
Mode Collapse for toy dataset?
#3 opened by hangg7 - 1
Results in dg_mnist.py
#4 opened by LinkWoong - 3
fixed batch size
#5 opened by SchafferZhang - 1
generating same sample
#6 opened by SchafferZhang