faster_rcnn_pytorch

faster_rcnn_pytorch copied to clipboard

ImportError: libcudart.so.10.0: cannot open shared object file.

2

I am trying to run the code on this [repository](https://github.com/yikang-li/MSDN) Running `./eval.sh` I get this error:  Configuration I am using: `torch.__version__` -> `0.4.1`...

CodHeK

RuntimeError in faster_rcnn.py

3

when I train on my own data,I meet an error when run the faster_rcnn.py,line 100,'rpn_loss_box = F.smooth_l1_loss(rpn_bbox_pred, rpn_bbox_targets, size_average=False) / (fg_cnt + 1e-4)'. It shows that "RuntimeError: Expected object of...

manyuyuya

For getting more accuracy in faster-rcnn , which parameters i have to tune (tuning parameters). please anybody provide the solution for that problem, actually my model is working but the...

devendraswamy

out of memory if don`t fix VGG16 param

1

If don`t fix pretrained VGG16`s parameters , the model will increasing untill memory booms. But if fix these parameters , it works. Why? code in train.py ``` for param in...

aRookieMan

error while running make.sh file in windows

1

Please tell how to run this code in windows. I ran make.sh file using GIT, but throws an error while compiling. Do we have to change anything in the make.sh...

ashacs12

No module named 'resource'，is the reason that I need run on the linux system?

yhyhhhhh

In anchor_target_layer.py,there is from ..utils.cython_bbox import bbox_overlaps, bbox_intersections, but cython_bbox doesn't exit!!

2

HueCheng

When I run demo.py, I receive the following feedback: AttributeError: 'module' object has no attribute 'roi_pooling_forward_cuda' Could u offer some suggestions? Many thanks

PaperLamp

How can I freeze the convolutional layers and remove some of the maxpooling layers in this implementation. Can anyone help me with this?

amlandas78

 I referred #83 so revised faster_rcnn.utils... But still error remains.. Could you suggest solution this error ?

KyuminHwang