luluoverflow

> @prolulu It seems the image path should be "data/cityperson/images" instead of "data/citypersons/images" In fact,before I ask this question I have set it to "cityperson"

@hdjsjyl @liuwei16 @jhb86253817 Excuse me, I have the same problem on both my computer and the server.Can you tell me why?Thank you very much!

keras ==2.0.6 tensorflow==1.13.1 opencv==3.4.6 Thank you very much for answering my question！

Yes.By the way I don't have GPU and cuda.

@jhb86253817 I appreciate you can try it for me. Now I have new question.LOL InvalidArgumentError (see above for traceback): Number of ways to split should evenly divide the split dimension,...

@jhb86253817 Which tensorflow did you install 1.4.1 or 1.4.1-gpu? And What version is your cuda?I have already used tensorflow 1.4.1 without gpu but do not install cuda in previous trials.So...

@jhb86253817 So you used python 3 ? And train_data = cPickle.load(fid) will be change to fid = pickle._Unpickler(fid) fid.encoding = 'latin1' train_data = fid.load() is it?

Using TensorFlow backend. num of training samples: 2975 WARNING:tensorflow:From /work/dependence/anaconda3/envs/py27/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py:2893: calling l2_normalize (from tensorflow.python.ops.nn_impl) with dim is deprecated and will be removed in a future version. Instructions for updating: dim...

@jhb86253817 In addition,Do you modify img_channel_mean in config.py?

ImportError: ***cython_bbox.so: undefined symbol: _Py_ZeroStructImportError: This problem occurs when compiling train.py and test.py. Why? Is it because the version of cython is too new? My cython version is 0.28. Or...