human_vehicle_parsing_platform icon indicating copy to clipboard operation
human_vehicle_parsing_platform copied to clipboard

A pytorch codebase for human parsing and vehicle parsing

Results 2 human_vehicle_parsing_platform issues
Sort by recently updated
recently updated
newest added

File "../../libs/_ext/__init__.py", line 4, in from .__ext.so import lib as _lib, ffi as _ffi ImportError: ../../libs/_ext/__ext.so: undefined symbol: state

您好,我运行了你的human_vehicle_parsing_platform代码报了附件图1的错误,我进行单步调试后发现是附件图2的y(维度8,48,193,193)和self.fuse_layer[0][x](x[1])维度不一致的问题,self.fuse_layer[0][x](x[1])维度是(8,48,194,194),附件图3是self.fuse_layer的网络结构,我不知道为什么self.fuse_layer[0][1](x[1])维度是(8,48,194,194)?这个错误该怎么改呢?在这个之前还遇到一个错误“RuntimeError: cuda runtime error (11) : invalid argument at /opt/conda/conda-bld/pytorch_1535491974311/work/aten/src/THC/THCGeneral.cpp:663” 我看了网上说是2080ti与低版本的pytorch和cuda不匹配问题,所以把cudnn.benchmark改成false,这个错误就消失了,但是遇到了前面提到的维度错误,不知道二者之间是不是有影响?数据集用的你发布的带分割标签的数据集,训练用的coarse_train_id.txt也是你公开的那个。(我运行的是train_test下的Deeplabv3的train.py,里面的run_train.sh运行不起来。config文件和cls_hrnet_w48_sgd_lr5e-2_wd1e-4_bs32_x100.yaml是从BraidNet文件下的复制过来的。) ![1](https://user-images.githubusercontent.com/62228852/189675527-a7f95cd2-c25a-4347-a076-f9bd31753326.jpg) ![2](https://user-images.githubusercontent.com/62228852/189675595-afb55a27-4831-4a85-b2f7-d631aed0ea02.jpg) ![3](https://user-images.githubusercontent.com/62228852/189675671-e15d5c2f-a49f-4929-9d97-5219d34d9f90.jpg) ![4](https://user-images.githubusercontent.com/62228852/189675899-0782368d-c1cd-4b98-b88e-a2786917616a.jpg)