Commit 45261f52 authored by Hongkun Yu's avatar Hongkun Yu Committed by A. Unique TensorFlower
Browse files

Update NCF readme.

PiperOrigin-RevId: 267535628
parent 6d1dd03d
...@@ -55,9 +55,13 @@ Note the ml-20m dataset is large (the rating file is ~500 MB), and it may take s ...@@ -55,9 +55,13 @@ Note the ml-20m dataset is large (the rating file is ~500 MB), and it may take s
Both the ml-1m and ml-20m datasets will be coerced into a common format when downloaded. Both the ml-1m and ml-20m datasets will be coerced into a common format when downloaded.
### Train and evaluate model ### Train and evaluate model
[ncf_keras_main.py](ncf_keras_main.py) is the Keras trainer that supports
features in TF 2.x. Users can train the model on both GPU and TPU.
To train and evaluate the model, issue the following command: To train and evaluate the model, issue the following command:
``` ```
python ncf_main.py python ncf_keras_main.py
``` ```
Arguments: Arguments:
* `--model_dir`: Directory to save model training checkpoints. By default, it is `/tmp/ncf/`. * `--model_dir`: Directory to save model training checkpoints. By default, it is `/tmp/ncf/`.
...@@ -65,7 +69,3 @@ Arguments: ...@@ -65,7 +69,3 @@ Arguments:
* `--dataset`: The dataset name to be downloaded and preprocessed. By default, it is `ml-1m`. * `--dataset`: The dataset name to be downloaded and preprocessed. By default, it is `ml-1m`.
There are other arguments about models and training process. Use the `--help` or `-h` flag to get a full list of possible arguments with detailed descriptions. There are other arguments about models and training process. Use the `--help` or `-h` flag to get a full list of possible arguments with detailed descriptions.
## Benchmarks (TODO)
### Training times
### Evaluation results
#!/bin/bash
set -e
./run.sh keras
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment