ankur-chr

Hi, I intend to training images which are both rectangular and high resolution. Which training flags should be used in this case? I checked the training/test tips link. However, it...

Hi, Are there any guidelines for training with a small dataset? I have a use case where trainA has around 850 images and trainB has only around 50 images. Will...

I'm getting these errors in the evaluation/test phase: Traceback (most recent call last): File "tools/test.py", line 326, in main instance_metric.update(instances, image_filename_list[i]) File "/content/drive/MyDrive/dissertation/dissertation/src/pdl/panoptic-deeplab/tools/../segmentation/evaluation/instance.py", line 56, in update add_colormap=False, scale_values=True) File...

I am getting the following inference output after 10k training iterations on a ResNet34 pre-trained backbone. Are the PQ values supposed to be so low? For ex: 0.34 (does this...

Hi, There is a pre-trained model linked in the description which converts day images to nighttime images. How was this model trained? I read the paper but am confused about...

@sauradip I tried to use the pretrained model. However, the day to night time conversion is producing not so good results. Sometimes the image is too dark (with no added...