search

MhLiao / TextBoxes_plusplus

TextBoxes++: A Single-Shot Oriented Scene Text Detector
Other
956 stars 281 forks source link

opencv error when training mnist data #84

Open redflower2017 opened 6 years ago

redflower2017 commented 6 years ago

Hi, I got an error message while training my MNIST data. I'm sure all the training and testing images come in three channels(RGB), uint8. Also, I've set force_color into true in the transform_param(both train and test) and set gpus value in solver parameters into zero(as shown in below). I've specified my only one GPU to use in PyCaffe. Can anyone help me solving my problem? Thanks.

Error message : ![training_error](https://user-images.githubusercontent.com/16350625/45541988-281b5680-b843-11e8-8e49-0b548ef6d202.png) OpenCV Error: Assertion failed ((scn == 3 || scn == 4) && (depth == CV_8U || depth == CV_32F)) in cvtColor, file /build/buildd/opencv-2.4.8+dfsg1/modules/imgproc/src/color.cpp, line 3959 terminate called after throwing an instance of 'cv::Exception' what(): /build/buildd/opencv-2.4.8+dfsg1/modules/imgproc/src/color.cpp:3959: error: (-215) (scn == 3 || scn == 4) && (depth == CV_8U || depth == CV_32F) in function cvtColor

liujianisme commented 3 years ago

add 'force_color':True, to train and test transform_param solved my question