Aashish Sharma

Can somebody elucidate why have the ADDA codes (this as well as the TensorFlow one) used two feature maps output from the discriminator instead of one? I am wondering why...

I am wondering if anybody has tried to visualize the features obtained from the source and target encoders respectively, to see if they indeed look similar or not? After the...

Hi @alex04072000 I've a question about training Linearization Net. I see that - First, you apply a randomly selected CRF ``crf`` (and its corresponding inverse CRF is ``invcrf``) to convert...

Hi @alex04072000 Thanks for your publishing your code and datasets. Going through the training and test datasets, I could not find any information about the ground-truth CRFs (or the cameras...

IMG_MEAN needs to be changed for CityScapes?

5

Hi @speedinghzl , I see the following has been used for CityScapes (during both training and evaluation)- `IMG_MEAN = np.array((104.00698793,116.66876762,122.67891434), dtype=np.float32)` I did some googling and found out the stats...

Hi @cydonia999, Thanks for your code. In your training, do you actually use full resolution images (by keeping patch_size=default=None)? If yes, could you please tell me your memory consumption? If...

batch-size >1 possible for training?

4

Hi @xwjabc, Thanks for your code! Could you please tell me if it is possible to have a higher batch-size (>1) for training? I see that when I try this...