Closed kevins99 closed 2 years ago
@kevins99 Did you solve this problem?
Did you solve this problem?
Hello @hhaAndroid @G-Naughty @kevins99 I'm facing the same error using the refine mask. I trained so many times. It had no issue. but having issue with some json files. i do not know how to solve this issue. Please, help me out if you have any solution.
I‘m facing the same error。<- _ ->
I solved this error just now, this error was caused by using numpy. In your code, must using operation such as "p[0::2] = w_scale", and you should modify it as "p[0::2] = p[0::2] w_scale". By this way that error can be solved.
I solved this error just now, this error was caused by using numpy. In your code, must using operation such as "p[0::2] = w_scale", and you should modify it as "p[0::2] = p[0::2] w_scale". By this way that error can be solved.
it works. But i don't figure out why i should change these lines?
Thanks for your error report and we appreciate it a lot.
Describe the bug While training a custom dataset on RefineMask(https://github.com/zhanggang001/RefineMask), I get the following error
This occurs when I run the training script. I have converted my dataset into the COCO annotation format and have ensured that my instance IDs do NOT repeat and also that my Polygons are sent as an array of polygons(https://discuss.pytorch.org/t/bug-in-pytorch-with-yolact/110573). The script runs perfectly with the default settings provided for COCO. Reproduction
Did you make any modifications on the code or config? Did you understand what you have modified? I changed the number of classes in the relevant areas of the config file, the path of the DATA_ROOT folder and the annotations file. Further, in the dataloader I have replaced the COCO classes with the relevant classes that I need.
What dataset did you use? I am currently using the PascalParts dataset(converted to the COCO format for Object level instance Segmentation). I have ensured that all the keys are present. Environment
TorchVision: 0.6.0a0+82fd1c8 OpenCV: 4.5.2 MMCV: 1.0.5 MMDetection: ('2.3.0',) MMDetection Compiler: GCC 5.5 MMDetection CUDA Compiler: 10.2
Bug fix