seekFire
seekFire
是在Scanning images环节出现了这个错误的, 如图：  我按照网上的指导把环境变量CUDA_LAUNCH_BLOCKING设为1，可是并没有用 我使用的GPU是三张NVIDIA GTX TITAN X，显存是12GB的 我要训练的模型是YOLOv4-P5，模型的参数量记得是70多M 请问这个错误是否是由于显存大小不够而导致的呢？
In lib/core/evaluate.py, function **calc_dists**, the Euclidean distance will be calculated under the condition: `if target[n, c, 0] > 1 and target[n, c, 1] > 1:` It seems that you exclude...
After building, when I run testcpu.py directly, the error occurs as follows: `Traceback (most recent call last): File "/home/bst/Documents/Projects/Official/Object_Detection/BBAVectors-Oriented-Object-Detection/models/DCNv2/testcpu.py", line 255, in example_dconv() File "/home/bst/Documents/Projects/Official/Object_Detection/BBAVectors-Oriented-Object-Detection/models/DCNv2/testcpu.py", line 175, in example_dconv output...
What's the meaning of [tmp2](https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation/blob/f97496fdaa5365ee33d44c7872da21375fb1a39c/lib/core/group.py#L226) ? Why you use **tmp2** to find out the [missing joints](https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation/blob/f97496fdaa5365ee33d44c7872da21375fb1a39c/lib/core/group.py#L229) ?
I can't understand the use of [these three lines](https://github.com/bailvwangzi/repulsion_loss_ssd/blob/fcf6c14be7e6ec2a1e146226a43491e744aef9c6/layers/functions/detection.py#L59-L61), it seems that they didn't change the value of any tensor.
PlateCommon.py中180行的addGauss函数用的是cv2.blur()，这是均值滤波，与函数名不符。应该为cv2.GaussianBlur()
In symbol/common.py, line 194 & 195, the variable "start_offset" is undefined before use it.
Given the code of these [two lines](https://github.com/674106399/JointBoneLoss/blob/a1f42a30ff5d638464c22b0e219472e5f85fa932/boneloss.py#L16-L17), I'm curious about the meaning of 3rd dimension. So for heatmap-based model, the 3rd dimension represents w*h, for regression-based model, the 3rd dimension...
In symdata/bbox.py, function "bbox_pred": Why "box_deltas" has the shape of [N, 4 * num_classes]? I can't understand what the "4*num_classes" represents