tzt101 / clade Goto Github PK

Hello,
Thank you for making the code available.
I'm trying to reproduce the mIoU for cityscapes. I want to make sure how should I test the generated images using drn --ms.
What is the resolution when you calculate the mIoU using DRN ? do you upsample the genereted results before testing mIoU or downsample the labels?

Thanks again

Hello,I am greatly inspired by your work.But when I train with --add_dist ,it show

(File "/home/CLADEv1/CLADEv1/train.py", line 76, in
for i, data_i in enumerate(dataloader, start=iter_counter.epoch_iter):
File "/usr/local/python3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 346, in next
data = self.dataset_fetcher.fetch(index) # may raise StopIteration
File "/usr/local/python3/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/python3/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/CLADEv1/CLADEv1/data/pix2pix_dataset.py", line 98, in getitem
dist_np = np.load(self.dist_paths[index])
IndexError: list index out of range)

Can you tell me how to solve it? Thank you。

Hello,
I want to fine-tune the available pretrained network for the ADK2016-Outdoor dataset.
The files for the generator network are available, but for training also the discriminator is needed.
I don't find the weights for the discriminator in the published folders.

Is it possible that you also share the pretrained discriminator, for fine-tuning the network?

Hello,

can you share the weights for the discriminator used to train the cityscpaes model?

Thanks in advance.