-
If you do not know the root cause of the problem, please post according to this template:
## Instructions To Reproduce the Issue:
Hello, I'm running the CondInst model which is based on detectron2…
-
12/11 11:43:01 d2.data.build]: Using training sampler TrainingSampler
[12/11 11:43:01 d2.data.common]: Serializing 117266 elements to byte tensors and concatenating them all ...
[12/11 11:43:05 d2.d…
-
作者你好，我跑了demo，2GB显存跑不起来提示显存不够，可以在哪改成CPU吗？或者在哪改batch？
-
In this function, when env.TORCH_VERSION > (1, 5), as I…
-
Hi, I'd like to train with different language datasets, such as Chinese, Korean, and Japanese, so I have to change the character set rather than the default setting.
Some detectron based models giv…
-
I haven’t found the ADQ method related code in the project. Haven’t I uploaded it yet?
-
I encountered this problem when I used my own data set to train BlendMask. I would like to ask, how can I solve it?
File "/home/excellence/anaconda3/envs/BlendMask/lib/python3.8/site-packages/torc…
-
Hello friends, could anyone guide me? how to train blendmask with my own coco datasets? Suggestion with some step by step process
-
I was able to train the blendmask and inference the model on my custom dataset which is prepared in coco format. The segmentation was good but the class_name on the bounding box was still person and b…