InstantWindy

AttributeError: module 'torch.jit' has no attribute 'get_trace_graph

11

Hi ! After installing tensorwatch, I run 'demo' code, it shows "AttributeError: module 'torch.jit' has no attribute 'get_trace_graph", how to solve it ? Thanks!

RuntimeError: torch/csrc/autograd/generated/VariableType.cpp:24095: expand_as: Assertion `jit::tracer::ArgumentStash::empty()` failed.

2

Hi! I use the tensorwatch on pytorch 0.4.1 version platform, it shows the error “RuntimeError: torch/csrc/autograd/generated/VariableType.cpp:24095: expand_as: Assertion `jit::tracer::ArgumentStash::empty()` failed.” Why is there such a mistake? How to slove it...

How to train my own dataset

10

Hi！ If I want to tain my own data with your model, how to run it? Thanks!

hi, Do you how to calculate the 'w,h,x,y' of the bounding box and normalize them? thanks.

Hi ! how do you calculate number of parameters and Gflops? Do you have code ? Thanks！

Hello,I use VOC2012 as the content image. However,The total number of iterations is 200,000,.I found that the final test effect failed to reach the result of the paper,the choice of...

Train my own dataset

2

Hi. I use this repro to train my own dataset. During the training process, the PSNR value of my test set was decreasing. What is the reason for this？ my...

Hi! you write the test command “python main.py test”. I wonder if there is no need to load weights for testing? Thanks！

How to train my own data

1

Hi. I want to train my own data. But the LR in my dataset is not aligned with the HR image pixels，when I use this network training, do I need...

Training parameters set

2

Hello ! could you porvide me the training parameters set? beacause I train the model ,I found it can not reach the paper performance . Thank you ！