Jie Zhang 张 杰

1. When you run train.py, the [labels.json](https://github.com/jiegzhan/multi-class-text-classification-cnn/blob/master/labels.json) will be saved. labels.json is a list with all labels. 2. When you run predict.py, take a look at [line 63](https://github.com/jiegzhan/multi-class-text-classification-cnn/blob/master/predict.py#L63), if you...

Actually, for each batch, there will be a batch_predictions list, which will be appended to all_predictions. Eventually, if you have 100 test examples, all predictions will have 100 numbers. Each...

What's your batch_size? Try changing the batch_size to 37. Or 67.

Which version of tensorflow? I was using tensorflow 0.9 to train the model.

https://github.com/jiegzhan/multi-class-text-classification-cnn-rnn/issues/2 Please look at the issue above.

~/Desktop/multi-class-text-classification-cnn/trained_model_1509570669/checkpoints$ ls checkpoint model-1000.meta model-1200.meta model-1400.meta model-600.meta model-800.meta model-1000.data-00000-of-00001 model-1200.data-00000-of-00001 model-1400.data-00000-of-00001 model-600.data-00000-of-00001 model-800.data-00000-of-00001 model-1000.index model-1200.index model-1400.index model-600.index model-800.index ~/Desktop/multi-class-text-classification-cnn/trained_model_1509570669/checkpoints$ ls ../../trained_model_1479757124/ Got a **trained_model_1509570669** folder.

~/Desktop/multi-class-text-classification-cnn$ python3 predict.py ./trained_model_1509570669/ ./data/small_samples.json CRITICAL:root:**Loaded the trained model: /home/ai-admin/Desktop/multi-class-text-classification-cnn/trained_model_1509570669/checkpoints/model-1400** INFO:root:The number of x_test: 1000 INFO:root:The number of y_test: 1000 2017-11-01 21:30:05.576209: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to...

labels are collected from training data automatically. https://github.com/jiegzhan/multi-class-text-classification-cnn/blob/8961f9277375c821023656235b8c41e13eb4b9a8/train.py#L39

try smaller batch_size and evaluate_every

https://github.com/jiegzhan/multi-class-text-classification-cnn/issues/13 After training, I was able to see the saved model files and run predict.py