Bradly-s

训练stgcn模型问题：环境问题

1

**paddle版本为develop版本** **报错信息如下**： [08/31 21:47:28] model_name : STGCN W0831 21:47:29.443328 4185452 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.6, Driver API Version: 11.6, Runtime API Version: 11.6 W0831 21:47:29.455291 4185452...

pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split((self.reg_max * 4, self.nc), 1) RuntimeError: shape '[70, 70, -1]' is invalid for input of size 164640

1

using train_dual.py、yolov9.yaml the erro occur when open compute_loss 

如何使用trans_seg_to_det_multi.py制作VOC2007_foggytrain数据集？

python main_da.py --hda 1 --cmt --output_dir out IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.002 Average Precision (AP) @[ IoU=0.50 | area=...