Open zjhthu opened 1 year ago
I run another experiment that only performs the object detection task, no error was encountered. I will check the difference between these two tasks.
The root is this line, RTMDet generates masks using img_shape
. My data augmentation config comes from the semi_coco_detection
. This config does not pad the image which will make img_shape
= resize_shape
. After adding the pad operation dict(type='Pad', size=image_size, pad_val=dict(img=(pad_val, pad_val, pad_val))),
, the error disappears.
But I am wondering why there is no error when I did not pad the image? Will MMDet pad the image itself?
RTMDet requires a fixed size of the input picture, while the size of the semi-supervised input picture is random. At present, the part of semi-supervised learning does not support instance segmentation
Any progress of semi-supervised learning on instance segmentation (like rtmdet)? Thanks.
Describe the bug I got the error when using RTMDet instance segmentation model with SemiBaseDetector for semi-supervised learning.
It seems the pseudo-masks generated by the teacher network do not work with the student network. I checked the
pos_gt_masks
variable, all masks are empty but with different shapes:Reproduction
I will upload the config if needed. The experiments are based on the customized dataset.
Environment
sys.platform: linux Python: 3.8.10 (default, Mar 13 2023, 10:26:41) [GCC 9.4.0] CUDA available: True numpy_random_seed: 2147483648 GPU 0: Tesla T4 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.2, V11.2.152 GCC: x86_64-linux-gnu-gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0 PyTorch: 1.9.0+cu102PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
TorchVision: 0.10.0+cu102 OpenCV: 4.7.0 MMEngine: 0.7.2 MMDetection: 3.0.0+ecac3a7