Hilmi Kumdakci

Results 8 comments of Hilmi Kumdakci

Error about train py-faster-rcnn with end2end.

could you solve the problem ?

Train my own data

You should modify these deploy.prototxt file to create train.prototxt where some examples are given in original caffe repository such as alexnet, vgg16. You can also convert your data into lmdb...

Train my own data

You can leave them as they are. They should be computed from Imagenet and should not matter a lot to change them. U can even comment them, the network should...

A problem when make

I solved this problem by replacing cv::Mat image= cv::imread(imageFilename, CV_LOAD_IMAGE_COLOR); line with cv::Mat image = cv::imread(imageFileName);

RGB to Grayscale Translation

Yes

caffe problem?

How did you install caffe ? From master or directly this one ?

"Expected more than 1 value per channel when training"

Has anyone found a solution?

Tensorrt supported detection networks

Thank you for answer. I will report here after I try faster-rcnn with different backbones.