pytorch-faster-rcnn

pytorch-faster-rcnn copied to clipboard

Is there a convenient way to train the network on a custom dataset? thanks!

sonnefred123

On the windows platform, can resource not be used?

Smallwhite999

train_faster_rcnn.sh: 12: train_faster_rcnn.sh: Syntax error: "(" unexpected

cyj199612

-> keep_inds = torch.cat([fg_inds, bg_inds], 0) (Pdb)

2

I got this problem,I change the x1 = float(bbox.find('min').text)...，and lower the thresh .but it did not work. so does anyone solved it,please tell me.thanks!!!

weihao86233531

When i Train my own model,after i downloaded the vgg16.pth to /data/imagenet_weights，“NameError: name 'sd' is not defined“，please help me

shida666

Training data consists of oriented bounding boxes rather than horizontal ones

4

I want to perform classification and detection only on my dataset of satellite images using Faster Rcnn. The problem is that there are very **dense objects** in the image and...

vsd550

Hi，thank you for your work. I want to know where is the code in yours for SVD for decomposing fully connected layers, corresponding to this part https://github.com/rbgirshick/py-faster-rcnn/blob/master/tools/compress_net.py?

Danee-wawawa

Training on new dataset, the speed slows down after certain iteration and error shows

4

Hi, I tried to implemented faster-rcnn on other dataset with json anno. I have worked it out when I change the json anno into xml and follows voc dataset. Now...

ymchen7

Hello, I am using the COCO dataset, A two-layer LSTM model, one layer for top-down attention, and one layer for language models. Extracting words with jieba I used all the...

cylvzj

Hi, I realize this repo is no longer actively maintained, but I would like to understand your reasoning behind these variables in the RPN loss calculation. **bbox_inside_weights** Purpose: Used as...

mathild7