colorfully-ybf
colorfully-ybf
ValueError: Unknown CUDA arch (8.6) or GPU not supported 有人在运行bash compile.sh的时候遇到过这个问题吗 后面我在运行脚本的时候都会报下面这个错误 ImportError: cannot import name 'deform_conv_cuda' from 'mmdet.ops.dcn' (/home/deep/colors/ReDet-master/mmdet/ops/dcn/__init__.py)
**Reproduction** ./tools/dist_train.sh configs/obb/fcos_obb/fcos_obb_r50_caffe_fpn_gn-head_4x4_1x_dota10.py 2 **Environment** the environment uesd to be ok. **Error traceback** If applicable, paste the error trackback here. ``` Traceback (most recent call last): File "./tools/train.py", line 153,...
File "tools/test.py", line 153, in main() File "tools/test.py", line 149, in main dataset.evaluate(outputs, args.eval, **kwargs) File "/home/deep/colors/OBBDetection-master/mmdet/datasets/obb/hrsc.py", line 126, in evaluate logger=logger) File "/home/deep/colors/OBBDetection-master/mmdet/core/evaluation/obb/obb_mean_ap.py", line 291, in eval_arb_map mean_ap, eval_results,...
关于对齐卷积
对3*3的卷积，一组offset生成一个维度，即对H*W*256，如果有512组offset（每个offset是3*3*2）送给3*3的AlignConv，输出的特征应该是H*W*512，也就是输出的特征的通道数应该和offset的数量是一致的，是这样吗，还是并非是这样操作？AlignConv输出的特征图的维度和offset的组数之间的对应关系应该是怎么样的？
cam.py
Traceback (most recent call last): File "/media/deep/Data/4_WSOD/pytorch-grad-cam/cam.py", line 133, in grayscale_cam = cam(input_tensor=input_tensor, File "/media/deep/Data/4_WSOD/pytorch-grad-cam/pytorch_grad_cam/base_cam.py", line 188, in __call__ return self.forward(input_tensor, File "/media/deep/Data/4_WSOD/pytorch-grad-cam/pytorch_grad_cam/base_cam.py", line 74, in forward outputs = self.activations_and_grads(input_tensor)...
python3 projects/WSL/tools/proposal_convert.py voc_2007_train datasets/proposals/MCG-Pascal-Main_trainvaltest_2007-boxes datasets/proposals/mcg_voc_2007_train_d2.pkl mat_data["boxes"] the mat_data has no attribute of boxes??
and how do we run other datasets on r3det?
repo里得DIOR下载链接只能下载DIOR，怎么获得DIOR-R？我用repo里得demo跑了一遍只能达到79.80，为什么会差了一个点？
when i use pytorch==1.7.1 there is the error that “AttributeError: module 'torch.distributed' has no attribute 'all gather base， all_gather_base function was added in PyTorch version 1.8.0？ when i use pytorch==1。9.0...