pytorch-faster-rcnn

pytorch-faster-rcnn copied to clipboard

Anchors problem with resnet152

1

when use pretrained model with Rsenet152，it occurs：  I guess it should be 12 anchors in rpn, but when i check cfg i found that there are 9 anchors ...

moment-ggw

'make' Error

2

**I ran the 'make'file, but it came an error like this:** python setup.py build_ext --inplace Traceback (most recent call last): File "setup.py", line 11, in include_dirs = [np.get_include(), '../common'], AttributeError:...

Jasonx001

Why the validation error is lower than training error

1

I have modified a original code so that I can plot training vs validation loss curves for the losses obtained after each epoch. But, I am getting validation loss less...

VikrantKarale

When I use a custom VOC format dataset, because the category is only 14 and does not match the weight of the pre training, the following error will be reported....

sure7018

How can l extract the features associated to each bounding box ?

11

Hello @ruotianluo, Let me first thank you for your clean code. l would like to extract the features associated to each bounding box using demo.py as you suggested : ```...

pinkfloyd06

Why set eval mode durint training?

6

Hi, I'm learning your code. And I found such codes in lib/nets/resnet_v1.py: ```python def train(self, mode=True): # Override train so that the training mode is set as we want nn.Module.train(self,...

zhoulukuan

_mask.so: undefined symbol: _Py_ZeroStruct

7

When I run the following command"./experiments/scripts/test_faster_rcnn.sh $GPU_ID pascal_voc vgg16" Such an error occurred： Logging output to experiments/logs/test_vgg16_voc_2007_trainval_.txt.2021-06-02_22-43-16 + [[ ! -z '' ]] + CUDA_VISIBLE_DEVICES=0 + time python ./tools/test_net.py --imdb...

ypxingxing

It is all right when I only switch the torch version to 1.1. But I find the loss is nan after 20 iters when I try to train the model...

xingaoli

which files should be changed if I want to use ZFnet?

shirleyatgithub

IndexError: list index out of range

1

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,...

devendraswamy