fpn.pytorch
fpn.pytorch copied to clipboard
jwyang
Pytorch implementation of Feature Pyramid Network (FPN) for Object Detection
When there is a problem with demo.py, we first use the demo.py given by the author @jwyang and report an error import error: no module named fast_ rcnn.faster_ rcnn_ cascade。...
Hello, this branch supports PyTorch1.0 or higher now?
The old version demo.py is not implemented for fpn specifically. The modified version is specifically updated for detecting objects by using fpn-trained model.
@jwyang I use python2.7(anaconda) and CUDA9.0 and sm_52(TITAN Xp) when I run sh make.sh, error occurs: ``` /mnt/lustre/hezhiqun/experiments/detection/cascade-rcnn_Pytorch/lib/model/nms/src/nms_cuda.c: In function ‘nms_cuda’: /mnt/lustre/hezhiqun/experiments/detection/cascade-rcnn_Pytorch/lib/model/nms/src/nms_cuda.c:14:22: error: dereferencing pointer to incomplete type boxes_host->size[0], ^...
进入代码目录 到lib，首先要编译c代码 sh make.sh,但是我得到了以下错误 fpn.pytorch/lib/model/roi_crop/src/roi_crop.c:10:30: error: dereferencing pointer to incomplete type int batchsize = inputImages->size[0]; ^ /fpn.pytorch/lib/model/roi_crop/src/roi_crop.c:11:39: error: dereferencing pointer to incomplete type int inputImages_height = inputImages->size[1]; 
Hi, sorry to bother you again.. I want to change the anchor size to detect some extremely small objects. So in the faster rcnn version, we can directly change the...
if I want to use your code to train on my dataset, where should I modify?
Here are my Trace backs: [session 1][epoch 1][iter 0] loss: 4.0006, lr: 1.00e-02 fg/bg=(128/384), time cost: 7.218862 rpn_cls: 0.6919, rpn_box: 0.1386, rcnn_cls: 2.8319, rcnn_box 0.3382 Traceback (most recent call last):...
@jwyang Hello, I trained fpn with resnext backbone on my own datasets and I get zero rcnn_box loss during the training, I wonder if there is something wrong ? meanwhile,...
I have run this code, based on resnet101, the best epoch result is 70.1, which is much less compared to faster-rcnn ---74.X, I want to know why?Can you tell me?Thank...
