Hi how do you process your input data, and if i want to trainning other data , this mode is ok for me ? Thanks!

(py3) λ python test.py -fr ktf -d data\movielns10k\ -b 512 --max_length 30 --r_l 30 --r_emb 30
Using TensorFlow backend.
2019-04-09 22:31:54.683881: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2019-04-09 22:31:54.924866: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1405] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.6325
pciBusID: 0000:01:00.0
totalMemory: 11.00GiB freeMemory: 9.10GiB
2019-04-09 22:31:54.943914: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1484] Adding visible gpu devices: 0
2019-04-09 22:31:55.258021: I tensorflow/core/common_runtime/gpu/gpu_device.cc:965] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-04-09 22:31:55.271662: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0
2019-04-09 22:31:55.280244: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] 0: N
2019-04-09 22:31:55.287898: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1097] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 3379 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)

---

Layer (type) Output Shape Param #

embedding_1 (Embedding) (None, 30, 30) 89280

---

masking_1 (Masking) (None, 30, 30) 0

---

lstm_1 (LSTM) (None, 30) 7320

---

dense_1 (Dense) (None, 2976) 92256

---

activation_1 (Activation) (None, 2976) 0

Total params: 188,856
Trainable params: 188,856
Non-trainable params: 0

---

filename : data\movielns10k\models\ktf\rnn_cce_ml30_bs512_ne*_gc100_e30_h30_Ug_lr0.1_nt1.ktf
['data\movielns10k\models\ktf\rnn_cce_ml30_bs512_ne49.969_gc100_e30_h30_Ug_lr0.1_nt1.ktf'
'data\movielns10k\models\ktf\rnn_cce_ml30_bs512_ne149.969_gc100_e30_h30_Ug_lr0.1_nt1.ktf']
Opening file (1)
Traceback (most recent call last):
File "test.py", line 168, in
main()
File "test.py", line 161, in main
evaluator = run_tests(predictor, f, dataset, args, get_full_recommendation_list=args.save_rank, k=args.nb_of_predictions)
File "test.py", line 55, in run_tests
recommendations = predictor.top_k_recommendations(viewed, k=k)
File "D:\Users\shwang\workspace\tests\LSTM-recommendation-model\neural_networks\rnn_base.py", line 105, in top_k_recommendations
output = self.model.predict_on_batch(X)
File "d:\Users\shwang\Anaconda3\envs\py3\lib\site-packages\keras\models.py", line 1041, in predict_on_batch
return self.model.predict_on_batch(x)
File "d:\Users\shwang\Anaconda3\envs\py3\lib\site-packages\keras\engine\training.py", line 1906, in predict_on_batch
self._feed_input_shapes)
File "d:\Users\shwang\Anaconda3\envs\py3\lib\site-packages\keras\engine\training.py", line 110, in _standardize_input_data
'with shape ' + str(data_shape))
ValueError: Error when checking : expected embedding_1_input to have 2 dimensions, but got array with shape (1, 30, 2976)

May I know the command line parameter when running LSTM_weight_tying(dim:100)

Hello, this project can run? I added the data set to do the preprocessing according to your original usage method and got an error during the train.
中文：您好，这个项目可以运行吗？我按照使用方法加了数据集做了预处理，在train期间出错了。

1. The default batch size is 16 which is the root cause of taking too much time to train the data.
   when I changed the batch size as 512, the convergence is much quicker.
2. I have adjusted your code to train data with keras by showing up the loss value and acc value of each iteration. But when loss value is less than 0.04 and acc value is hight than 0.99. I want to generate the weight file. How do I to control when to generate that weight file?

Hello, I download movielens dataset 1m from https://grouplens.org/datasets/movielens/1m/
and use preprocess.py to process ratings.dat, as your command shown in the page.

And I got a folder called ratings containg data, models and results subfolders, everything in great!

However, when I type python train.py -fr tf -d ...ratings\ I got error message: ValueError: invalid literal for int() with base 10: '2000-12-31'
The data themselves are from preprocess.py, how can I fix it? thanks.

there is no attribute or method named "self.tarining"