faster_rcnn_pytorch
faster_rcnn_pytorch copied to clipboard
Faster RCNN with PyTorch
why so quickly? even 17fps obtianed?
cd /faster_rcnn_pytorch/faster_rcnn 到该路径, ./make.sh 出现ModuleNotFoundError: No module named 'torch'
You wrote "RoI Pooling layer with C extensions on CPU (only forward)" Can I run test/forward (make installation steps) without nvidia-gpu (cuda, cudnn etc)?
‘ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead.’ was reported when executing 'python3 build.py'. Then i fixed this problem using the link https://blog.csdn.net/ShuqiaoS/article/details/88420326 But a new error occured, Traceback...
how to download it?
Hi, I have some question about VGGnet_fast_rcnn_iter_70000.h5. How do you get this model? Did this model pretrained on Pascal VOC 2007?
File "./tools/trainval_net.py", line 139, in max_iters=args.max_iters) File "/content/drive/My Drive/TF-MODEL/tf-faster-rcnn/tools/../lib/model/train_val.py", line 377, in train_net sw.train_model(sess, max_iters) File "/content/drive/My Drive/TF-MODEL/tf-faster-rcnn/tools/../lib/model/train_val.py", line 278, in train_model blobs = self.data_layer.forward() File "/content/drive/My Drive/TF-MODEL/tf-faster-rcnn/tools/../lib/roi_data_layer/layer.py", line 97,...
when I run ./make.sh there were 3 traceback Traceback (most recent call last): File "setup.py", line 59, in CUDA = locate_cuda() File "setup.py", line 45, in locate_cuda raise EnvironmentError('The nvcc...