- I'm working as a researcher at AI Center of Samsung Life Insurance.
- NLP, including Language Modeling and Represenation Learning
- And also ML, Recommend system
- Fine-tuning and serving large language model
- Retrieval augmented generation(RAG)
Applied weight tying technique to RNN based recommendation model. Implemented with Tensorflow and Keras.
(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)
Hi how do you process your input data, and if i want to trainning other data , this mode is ok for me ? Thanks!
there is no attribute or method named "self.tarining"
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。
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.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.