pva-faster-rcnn

pva-faster-rcnn copied to clipboard

ghost

RPN的loss 和最后的loss是2部分。怎么训练的呢，end-2-end 将2部分的4个loss相加训练？还是 two step 交替训练rpn和最后的分类回归？ why __C.TRAIN.HAS_RPN=False?

ChChwang

IOError: [Errno 2] No such file or directory: 'models/pvanet/cfgs/train.yml' 请问这个train.yml文件，存在，却一直说找不到，你知道该怎么解决吗？

dongzhenguo2016

请问，怎么使用docker运行pvanet,因为在服务器上配caffe环境太难了

dongzhenguo2016

Error: Caffe.LayerParameter" has no field named "smooth_l1_loss_param"

6

Hi I am trying to use tools/test_net.py on my own test data with the model models/pvanet/pva9.1/PVA9.1_ImgNet_COCO_VOC0712plus.caffemodel and models/pvanet/pva9.1/faster_rcnn_train_test_21cls.pt However, the error_message is: W0503 15:56:22.701463 25382 _caffe.cpp:123] Use this instead (with...

yzhang123

Is it means that bounding box after NMS and before NMS???

Bigwode

keep = np.where((ws >= min_size) & (hs >= min_size))[0];Check failed: error == cudaSuccess (9 vs. 0) invalid configuration argument

2

I reallly crazy about this?could you take a look at it~thankyou very much /raid5/Julia/pva-faster-rcnn/tools/../lib/rpn/proposal_layer.py:180: RuntimeWarning: invalid value encountered in greater_equal keep = np.where((ws >= min_size) & (hs >= min_size))[0] F0112...

QueenJuliaZxx

PVANet Lite version

5

Thx for update. I notice you have removed PVANet Lite version. So can you provide pretrained classification PVA-lite model on ImageNet? Since the highly efficient of Lite version is so...

XiongweiWu

check failed: target_blobs.size() == source_layer.blobs_size() (1 vs. 0). Incompatible number of blobs for layer conv1_1/conv

4

i'm using pva-faster-rcnn on windows+cuda8.0. I'm trying to training my own data (1 object class and background) with the following code: python tools/train_net.py --gpu 0 --solver models/pvanet/example_train/solver.prototxt --weights models/pvanet/pva9.1/PVA9.1_ImgNet_COCO_VOC0712.caffemodel --iters...

lixiang-ucas

Hi i am trying to run ./tools/test_pvanet.py. It works fine in CPU but in GPU it fails. figured out that im_detect function fails with `F0213 23:08:03.355202 19911 roi_pooling_layer.cu:88] Check failed:...

shridharkini6