Grid-Anchor-based-Image-Cropping-Pytorch
Grid-Anchor-based-Image-Cropping-Pytorch copied to clipboard
lld533
Compatible with Python3 & PyTorch 1.0+ on Ubuntu
When I perform"sudo bash make_all.sh", `Compiling rod_align kernels by nvcc... In file included from rod_align_kernel.cu:2:0: rod_align_kernel.h:4:21: fatal error: THC/THC.h: No such file or directory #include ^ compilation terminated. ` `FAILED:...
The link shows that the dataset and the pretrained model are moved to Trash. Could you please fix it? Thanks.
i've Built and installed source code of roi_align_api and rod_align_api. but while running roi_align.py -> roi_align_api.forward(), outputs are all zeros. all params are default, i didn't change anything. aligned_height :...
the config： pytorch=1.3.0 torchvision=0.4.1 cuda=10.0 cudatoolkit=10.0 the GPUs are tesla V100-sxm2-16gb After I modified the make.sh‘s gpu-arch and made it，when running the demo_eval.py，it comes the fault： segmentation fault (gdb) f...
When I installed the roi and rod.I met some error.Just like this. `error: command 'D:\\application\\visual_studio\\VC\\Tools\\MSVC\\14.10.25017\\bin\\HostX64\\x64\\cl.exe' failed with exit status 2` Did anybody met this problem?Thank u for u help.
Could you provide the weights saved along with the architecture? I am trying to convert the model file to tensorflow but cant without the architecture saved along with the weights....
I run test with both PyTorch 1.2 and PyTorch 0.4.1 version, some top1 cropping results are different For examples image number: 220865 PyTorch 0.4.1: https://www.flickr.com/photos/186202377@N03/49290064682/in/dateposted-public/ PyTorch 1.2: https://www.flickr.com/photos/186202377@N03/49289369793/in/dateposted-public/ image number:221273...
I am unable to use mobilenetv2_0.5 mobilenetv2_0.75 and mobilentv2_1.0 pretrained weights.....I get an error in demo_eval.py in line 63 i.e. in load_state_dict
The detected CUDA version (10.1) mismatches the version that was used to compile PyTorch (10.2). Please make sure to use the same CUDA versions.
my enviroonment is windows,how to solve this problem
