DL-ljw

The data and label should have the same first dimension.

1

Hi, I encounter the following problem, hoping for a reply: I1208 08:51:16.048475 7276 layer_factory.hpp:77] Creating layer rpn_loss_cls F1208 08:51:16.049386 7276 loss_layer.cpp:19] Check failed: bottom[0]->shape(0) == bottom[1]->shape(0) (2 vs. 1) The...

Test on VOC2012

2

Hi, @szq0214. Sorry for bothering you again. Can you tell me what I should change to test on VOC2012, the default is 2007.

small batchsize has a lower mAP.

3

Hi, @szq0214: I only have two GTX 1080 GPUs. I want to reproduce you GRP-DSOD. When I change the batch_size and accum_batch_size to 6 and 30, the mAP is just...

out of memory

6

Sorry for bothering you again. When I train it with one 1080 GPU with batchsize of 1. I got the following mistakes. How can I solve it? 2018-05-10 13:42:49: step247692...

InvalidArgumentError (see above for traceback): input must have at least k columns

4

When I use SAR images, I got the following error. Can you help me to solve it? InvalidArgumentError (see above for traceback): input must have at least k columns [[Node:...

How to make the annotation?

2

Hi, thanks for your work. I want to annotate my own data with 8 parameters rather than the 4 parameters（PASCAL VOC uses the labelimg). Is there tools to do this?...

can`t find -lhdf5_serial_hl

4

Hi @liulei01 , sorry for bothering you. When I make caffe, I got the following information. What I should do? AR -o .build_release/lib/libcaffe.a LD -o .build_release/lib/libcaffe.so.1.0.0-rc3 /usr/bin/ld: 找不到 -lhdf5_serial_hl /usr/bin/ld:...

We are looking forward your pytorch version. Thanks for your great work.