search

zhaoweicai / mscnn

Caffe implementation of our multi-scale object detection framework
404 stars 211 forks source link

Check failed: mean_values_.size() == 1 || mean_values_.size() == channels #69

Open Solomon1588 opened 7 years ago

Solomon1588 commented 7 years ago

I tried to train MSCNN on KITTI dataset with script named "train_mscnn.sh" within mscnn-7s-576-2x, but I got an error like this: _Check failed: meanvalues.size() == 1 || meanvalues.size() == channels Specify either 1 meanvalue or as many as channels: 0 .This error happened at image_gt_data_layer.cpp:261, it seems that there is a mismatch between mean_values and determined value, and the details as follow. I wonder how can I solve this problem, thanks @zhaoweicai 


I0417 23:36:14.074622  6580 image_gt_data_layer.cpp:170] Number of images: 1
I0417 23:36:14.074637  6580 image_gt_data_layer.cpp:171] Number of colleting images: 1
I0417 23:36:14.074650  6580 image_gt_data_layer.cpp:177] class 0 has 0 samples
I0417 23:36:14.074654  6580 image_gt_data_layer.cpp:177] class 859 has 4226536 samples
I0417 23:36:14.074656  6580 image_gt_data_layer.cpp:183] Shuffling data
I0417 23:36:14.337412  6580 image_gt_data_layer.cpp:213] output data size: 4,0,576,768
I0417 23:36:14.337682  6580 image_gt_data_layer.cpp:235] output label size 0 : 4,6,72,96
I0417 23:36:14.337862  6580 image_gt_data_layer.cpp:235] output label size 1 : 4,6,72,96
I0417 23:36:14.338026  6580 image_gt_data_layer.cpp:235] output label size 2 : 4,6,36,48
I0417 23:36:14.338183  6580 image_gt_data_layer.cpp:235] output label size 3 : 4,6,36,48
I0417 23:36:14.338345  6580 image_gt_data_layer.cpp:235] output label size 4 : 4,6,18,24
I0417 23:36:14.338505  6580 image_gt_data_layer.cpp:235] output label size 5 : 4,6,18,24
I0417 23:36:14.338654  6580 image_gt_data_layer.cpp:235] output label size 6 : 4,6,9,12
I0417 23:36:14.338812  6580 image_gt_data_layer.cpp:250] output gt boxes size: 1,7,1,1

F0417 23:36:14.338837  6580 image_gt_data_layer.cpp:261] Check failed: mean_values_.size() == 1 || mean_values_.size() == channels Specify either 1 mean_value or as many as channels: 0
*** Check failure stack trace: ***
    @     0x7feea0e635cd  google::LogMessage::Fail()
    @     0x7feea0e65433  google::LogMessage::SendToLog()
    @     0x7feea0e6315b  google::LogMessage::Flush()
    @     0x7feea0e65e1e  google::LogMessageFatal::~LogMessageFatal()
    @     0x7feea175966e  caffe::ImageGtDataLayer<>::DataLayerSetUp()
    @     0x7feea178193d  caffe::BaseDataLayer<>::LayerSetUp()
    @     0x7feea1781d77  caffe::BasePrefetchingDataLayer<>::LayerSetUp()
    @     0x7feea16f63e6  caffe::Layer<>::SetUp()
    @     0x7feea180e3df  caffe::Net<>::Init()
    @     0x7feea180c69b  caffe::Net<>::Net()
    @     0x7feea1687191  caffe::Solver<>::InitTrainNet()
    @     0x7feea168697a  caffe::Solver<>::Init()
    @     0x7feea16863c4  caffe::Solver<>::Solver()
    @     0x7feea17fdbaf  caffe::SGDSolver<>::SGDSolver()
    @     0x7feea1806e05  caffe::Creator_SGDSolver<>()
    @           0x421a66  caffe::SolverRegistry<>::CreateSolver()
    @           0x41c80e  train()
    @           0x41ee2d  main
    @     0x7fee9f61e830  __libc_start_main
    @           0x41b349  _start
    @              (nil)  (unknown)
Aborted (core dumped)```
zhaoweicai commented 7 years ago

It looks like your input image has 0 channel. Just try to input the typical RGB images.

penghaoxiao commented 3 years ago

I want to train single channel images with cascade RCNN, which need to be modified

I1026 15:39:55.119340 15373 detection_data_layer.cpp:142] num: 0 /VOCdevkit/VOC2020/JPEGImages/3_3&18.tiff 1 1000 1000 windows to process I1026 15:39:55.119726 15373 detection_data_layer.cpp:150] Number of images: 53 I1026 15:39:55.119731 15373 detection_data_layer.cpp:155] class 0 has 0 samples I1026 15:39:55.119736 15373 detection_data_layer.cpp:155] class 1 has 803 samples I1026 15:39:55.119740 15373 detection_data_layer.cpp:163] Random aspect shuffling data I1026 15:39:55.120517 15373 detection_data_layer.cpp:233] output data size: 2,1,1024,1024 I1026 15:39:55.120568 15373 detection_data_layer.cpp:254] output label size 0 : 2,6,64,64 I1026 15:39:55.120611 15373 detection_data_layer.cpp:254] output label size 1 : 2,6,64,64 I1026 15:39:55.120657 15373 detection_data_layer.cpp:254] output label size 2 : 2,6,64,64 I1026 15:39:55.120709 15373 detection_data_layer.cpp:254] output label size 3 : 2,6,64,64 I1026 15:39:55.120752 15373 detection_data_layer.cpp:254] output label size 4 : 2,6,64,64 I1026 15:39:55.120791 15373 detection_data_layer.cpp:254] output label size 5 : 2,6,64,64 I1026 15:39:55.120843 15373 detection_data_layer.cpp:254] output label size 6 : 2,6,64,64 I1026 15:39:55.120882 15373 detection_data_layer.cpp:254] output label size 7 : 2,6,64,64 I1026 15:39:55.120923 15373 detection_data_layer.cpp:254] output label size 8 : 2,6,64,64 I1026 15:39:55.120961 15373 detection_data_layer.cpp:270] output gt boxes size: 1,8,1,1 F1026 15:39:55.120966 15373 detection_data_layer.cpp:281] Check failed: meanvalues.size() == 1 || meanvalues.size() == channels Speci Check failure stack trace: @ 0x7fbba1f655cd google::LogMessage::Fail() @ 0x7fbba1f67433 google::LogMessage::SendToLog() @ 0x7fbba1f6515b google::LogMessage::Flush() @ 0x7fbba1f67e1e google::LogMessageFatal::~LogMessageFatal() @ 0x7fbba26d1478 caffe::DetectionDataLayer<>::DataLayerSetUp() @ 0x7fbba2617775 caffe::BasePrefetchingDataLayer<>::LayerSetUp() @ 0x7fbba2564b5c caffe::Net<>::Init() @ 0x7fbba25673ae caffe::Net<>::Net() @ 0x7fbba2571b65 caffe::Solver<>::InitTrainNet() @ 0x7fbba2572f95 caffe::Solver<>::Init() @ 0x7fbba25732af caffe::Solver<>::Solver() @ 0x7fbba275cde1 caffe::Creator_SGDSolver<>() @ 0x416c5a caffe::SolverRegistry<>::CreateSolver() @ 0x40e25d train() @ 0x4097d3 main @ 0x7fbba0e5f840 __libc_start_main @ 0x40a1d9 _start @ (nil) (unknown)