search

jiegzhan / multi-class-text-classification-cnn-rnn

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.
https://www.kaggle.com/c/sf-crime/data
Apache License 2.0
599 stars 262 forks source link

Unsuccessful TensorSliceReader constructor #35

Open pradiepsingh opened 6 years ago

pradiepsingh commented 6 years ago

Hi Jie getting below error any idea who to rectify this error:

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for ./checkpoints_1517652366/model-0 [[Node: save/RestoreV2_36 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_36/tensor_names, save/RestoreV2_36/shape_and_slices)]]

danielduckworth commented 6 years ago

Are you using the dataset with this repository or a different dataset?

chocosando commented 6 years ago

I have same problem when I'm trying to my own data (same structure). Would you help me ? Thank you.

mannamh commented 6 years ago

I have the same problem when I'm trying my own data. Any updates on this?

harirajeev commented 6 years ago

me too facing the same issue.

Nadedic commented 6 years ago

I have the same case and I tracked it down to train.py where the session starts to run(also the other two run functions written before this one):

sess.run(tf.global_variables_initializer())

Showing an internal error: The Session graph is empty. Add operations to the graph before calling run(). Which makes no sense, after initializing the graph, the inilization is called and the layers should be loaded. I am not sure what exactly is happening there.

saja1994 commented 6 years ago

Please, has any one solved this issue?