Lvhhhh

@sergeyk when i write python selective_search.py . and it say: scipy.io.matlab.miobase.MatReadError: Mat file appears to be empty. my platform is windows.and i change"\dev\null" to "NUL".

@CLTFOREVER my MATLAB path is "D:\matlab\bin".but i change mc="D:\matlab\bin\matlab" it dos not work." scipy.io.matlab.miobase.MatReadError: Mat file appears to be empty"

i have the same problem and still not solved. please check the path of your picture and i have not seen mat produced by matlab

> i have an issue > after first epoch > current_index = (self.batch_index * self.batch_size) % self.n > ZeroDivisionError: integer division or modulo by zero > pls help me i...

> > > i have an issue > > > after first epoch > > > current_index = (self.batch_index * self.batch_size) % self.n > > > ZeroDivisionError: integer division or...

> i have an issue > after first epoch > current_index = (self.batch_index * self.batch_size) % self.n > ZeroDivisionError: integer division or modulo by zero > pls help me delete...

i agree~

now. it have these problem sing TensorFlow backend. 2017-09-16 10:22:56.473879: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could...

the test_params.json { "data":"./pic", "pspath": "./prediction", "batch_size": 1, "w_path": "model_weight.hdf5", "max_q_size": 1, "verbose": 1 } the error message: Using TensorFlow backend. Loading pretrained cost weight... 2017-09-18 13:54:29.217078: W tensorflow/core/platform/cpu_feature_guard.cc:45] The...

1.i use the newest version of your code. when i python train.py i found the loss is bigger and bigger. train_params.json are followed: { "weight_save_path": "model/model_weight.hdf5", "period": 1, "verbose": 1,...