faster_rcnn_pytorch

faster_rcnn_pytorch copied to clipboard

Hi there, I got some problem extracting feature from a given roi. The code I wrote is ```python def _im_exfeat(self, image, roi): """ image: ( ndarray ) (H x W...

dichen-cd

Wrong format for bounding boxes

4

It seems that the network uses `x1,y1,x2,y2` format for bounding boxes instead of `x,y,w,h` used in the paper. I think this is a pretty major difference that can affect training...

Rizhiy

Train new dataset: zeros after conv3 in vgg16

19

I am trying to train the model with my own dataset. Sometimes , I got this error ```Traceback (most recent call last): File "train.py", line 127, in net(im_data, im_info, gt_boxes,...

kduy

import cv2 error

1

when I run the train.py, the error `ImportError: /usr/share/Anaconda2/lib/python2.7/site-packages/torch/lib/libgomp.so.1: version `GOMP_4.0' not found (required by /opt/OpenBLAS/lib/libopenblas.so.0) ` happens. How can I fix it?

XavierLinNow

How to support multigpu?

2

Hello, How to modify the repo to support multi gpu training?

philokey

The training process is not the same as the paper.

1

The paper use as training method called "Alternating Training", but the code just train the model end to end.

mariolew

Hi, @longcw , could you pls provide any hint of adapting the ROI pooling function for fast rcnn training? Thanks a lot !

shanyuhu

I've seen other implementations allow random transformations to train images like rotations, horizontal shifts and zooms. Can you help me with this or direct me to some thread or example...

harishkrishnav

Output from the reg layer in RPN.

1

**The reg layer in RPN has 4k outputs encoding the coordinates of k boxes.**(from the paper) So what actually this layer predicts?Is it predicting the 4 coordinates of boundary boxes...

blitu12345

mAP

1

Hi, Would you mind to show the mAP of the provided model file? Thanks a lot

D-X-Y