Javin
Results
2
issues of
Javin
为什么在20个类别上的数据集上进行微调过后进行指定类别推理的时候就报错了，中间特征图的大小被固定成训练的类别了这是什么原因牙官方预训练过后的就不会有这个问题。x_cat = torch.cat([xi.view(shape[0], self.nc + self.reg_max * 4, -1) for xi in x], 2) File "/home/xgrids/ZJJ/code/yoloe/ultralytics/nn/modules/head.py", line 486, in x_cat = torch.cat([xi.view(shape[0], self.nc + self.reg_max * 4, -1) for xi...
Hello, great job. I would like to ask why the point cloud scene keeps displaying and reading, and the software is also stuck here.