RyanCV

Hi, I followed the steps of Fast R-CNN, however, when I run `make -j16 && make pycaffe`, I also have the following problem. I load cuda/7.5, opencv2.4.10, python2.7.10. src/caffe/layers/cudnn_conv_layer.cu(142): error:...

@jjsjunior do you mean shuffle here: `index_queue = tf.train.range_input_producer(range_size, num_epochs=None, shuffle=True, seed=None, capacity=32)`, I have tried "True" and "False", but it didn't help. @fisakhan : what do you mean by...

@alanMachineLeraning How did you solve this problem of using center loss during training? I also have this kind of inf of center loss after 3 epochs during finetuning of facenet.

@chaoyuaw I followed your instruction as follows: ``` 1. Download FFmpeg (git clone https://github.com/FFmpeg/FFmpeg.git). 2. Go to FFmpeg home, and git checkout 74c6a6d3735f79671b177a0e0c6f2db696c2a6d2. 3. make clean 4. ./configure --prefix=${my_ffmpeg} --enable-pic...

It works now using `./configure --prefix=./my_ffmpeg --enable-pic --disable-yasm --enable-shared`

@Tylerjoe try this, my_ffmpeg is the new folder you need to create before run: `./configure --prefix=./my_ffmpeg --enable-pic --disable-yasm --enable-shared`

@lijinchao2007 @Zhongdao > graph_propagation在生成最终聚类结果的时候，max_sz参数影响很大，而且难以确定。 I also found the same issue, if max_sz=900, then it gives two clusters; if max_sz=850, the it gives 35 clusters. Any idea how to tune max_sz?...

It works, thanks @rockrush . But how to solve the following problem: OpenCV Error: Assertion failed (matRead(_modelName + ".xP", xP1f) && matRead(_modelName + ".xN", xN1f)) in trainStageI, file /media/BING_Linux/Src/Objectness.cpp, line...

@sunshineatnoon , I have the following error similar to yours, do u know how to solve it?? Invalidate class name in /media/BING_Linux/Src/DataSetVOC.cpp:125 OpenCV Error: Assertion failed (Invalidate class name )...

@gpu Thanks for your help. I add `set(OpenCV_LIBS "/cluster/6.2/opencv/2.4.10/lib/libopencv_core.so")`, and it solved the error of `FindOpenCV.cmake`.