Mingyu Kim
Mingyu Kim
When I looked through your code of NCSN_MNIST.py, I'm wondering that ConditionalBatchNorm2d/ConditionalInstanceNorm2d/CRPBlock/CondCRPBlock/CondRCUBlock/CondMSFBlock/CondRefineBlock/ConvMeanPool/MeanPoolConv/ConditionalResidualBlock/CondRefineNetDilated and so on. Actually, I'm not able to understand what prefix such as "Cond", "Cons", "CRP", "RCU", "MSF"....
 - This Table 2 indicates ablation study of training components for VP/VE models in terms of performance. - In this table, we can choose several training configuration such as...
Thanks for sharing your work in public. Regarding to the configuration attached in this GitHub, I thought this version might be slightly different than what you used for representing numerical...
In the current commit, every execution should call the `create_transform` function at the in `/src/datasets/__init__.py`. However, in NVS experiments, we do not need to have this function, so that we...