sgan

sgan copied to clipboard

How to map real world coordinates back to pixel space to visualize the results of the model?

1

The paper describes that the data is converted to real-world coordinates. Can I know how to map back to pixel space to visualize in the video image as shown in...

VishalSowrirajan

The `make_mlp` function appends also to the last layer batch normalization, dropout, and the activation function. This might be problematic, as the output of such function is used also to...

nicosacco

Bumps [numpy](https://github.com/numpy/numpy) from 1.14.5 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

ValueError: could not broadcast input array from shape (2,15) into shape (2,16)

3

 When I ran train.py, this bug appeared. Later, I adjusted the torch version and no longer reported the error, but it appeared again when I ran evaluate_model.py. I don't...

liusui652

EVALUATION PROBLEM

1

Hello, when I run the evaluate script, I always get this error. What can I do please?  Thanks

MZ82020

'NoneType' object is not subscriptable

7

I have met the problem, when I run my the train.py. Traceback (most recent call last): File "train.py", line 595, in main(args) File "train.py", line 160, in main batch_norm=args.batch_norm) File...

fengxianghu

This pull requests addresses incorrect validation loss calculation and checkpoint saving behavior due to unintentional aliasing. Specifically: - the lists used to calculate the validation metrics referred to the same...

456263

Can you provide the super parameters in the code？

2

I want to reproduce the indicators of the code in the paper. However, the default parameters do not get the desired results，Can you provide the super parameters in the code？such...

woshanglaile

Does the parameter "num_iterations" really work?

1

ren-xiaoke

Evaluation error for model without pooling module (KeyError : 'g_state')

3

Hi I have trained the model for zara1 (8 timestamps) by using the pretrained model parameters (which I got by using print arguments of your pretrained model). Evaluation script is...

iamrjkunal