Detectron.pytorch

Detectron.pytorch copied to clipboard

(python3) mike@amax:/data2/mike/Detectron.pytorch/lib$ sh make.sh running build_ext building 'utils.cython_bbox' extension creating build creating build/temp.linux-x86_64-3.6 creating build/temp.linux-x86_64-3.6/utils gcc -pthread -B /home/mike/anaconda3/envs/python3/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/mike/anaconda3/envs/python3/lib/python3.6/site-packages/numpy/core/include -I/home/mike/anaconda3/envs/python3/include/python3.6m...

chuxiang93

Hi everyone, I am doing a comparison with others object detection networks and I have a question: How can I properly variate the threshold to obtain different recall values? I...

gsaibro

Hi, I trained my dataset (only one class) on your code and train the network following "e2e_faster_rcnn ResNet-50.yaml". However, I find that loss_cls is larger than loss_rpn_cls, which is not...

At1a8

cannot I finetune from coco-pretrained models

4

### Expected results In the caffe2 implementation, there is a field TRAIN.WEIGHTS which allows us to use models pretrained on datasets such as coco. Can I merely use pretrained resnet...

CoinCheung

Hi, I have a question that confuses me. I use resnet50-fpn backbone The image will be scaled before sending to network, but I found the bounding box coordinates were not...

Redaimao

Hi, I have a small question. During evaluation, the detectron outputs all the keypoints' location, and some logit and probability associated with it. There is no binary tag regarding if...

rohitrango

If multiple datasets are specified for training, what is the sampling ratio between these datasets?

1

For example, if I have dataset A with 1000 images and dataset B with 500 images, will data from A and B be sampled with a 1:1 ratio or 2:1...

yimang

https://github.com/roytseng-tw/Detectron.pytorch/blob/8315af319cd29b8884a7c0382c4700a96bf35bbc/tools/train_net_step.py#L193 Why you use `original_batch_size` instead of `original_batch_size * original_iter_size` ? Is the reason that you ignore the 'original_iter_size' because its default value is 1?

RanTaimu

897051629

1. yaml.parser.ParserError caused by incorrect indentation in e2e_faster_rcnn_X-101-64x4d-FPN_1x.yaml COMMAND: ``` python tools/test_net.py --dataset coco2017 --cfg configs/baselines/e2e_faster_rcnn_X-101-64x4d-FPN_1x.yaml --load_detectron /path/to/weights/e2e_faster_rcnn_X-101-64x4d-FPN_1x.pkl ``` ERROR : ``` "expected , but found %r" % token.id, token.start_mark)...

1Konny