config.yaml

# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

workspace: "paddlerec.models.demo.movie_recommand"

# list of dataset
dataset:
- name: dataset_train # name of dataset to distinguish different datasets
  batch_size: 128
  type: QueueDataset 
  data_path: "{workspace}/data/train"
  sparse_slots: "logid time userid gender age occupation movieid title genres label"
  dense_slots: ""
- name: dataset_infer # name
  batch_size: 128
  type: DataLoader
  data_path: "{workspace}/data/test"
  sparse_slots: "logid time userid gender age occupation movieid title genres label"
  dense_slots: ""
- name: dataset_online_infer # name
  batch_size: 10
  type: DataLoader
  data_path: "{workspace}/data/online_user/test"
  sparse_slots: "logid time userid gender age occupation movieid title genres label"
  dense_slots: ""

# hyper parameters of user-defined network
hyper_parameters:
  # optimizer config
  optimizer:
    class: Adam
    learning_rate: 0.001
    strategy: async
  # user-defined <key, value> pairs
  sparse_feature_number: 60000000
  sparse_feature_dim: 9
  dense_input_dim: 13
  fc_sizes: [512, 256, 128, 32]

# train
mode: runner_train

## online or offline infer
#mode: runner_infer
runner:
- name: runner_train
  class: train
  save_checkpoint_interval: 1 # save model interval of epochs
  save_inference_interval: 1 # save inference
  save_checkpoint_path: "increment" # save checkpoint path
  save_inference_path: "inference" # save inference path
  epochs: 10
  device: cpu

- name: runner_infer
  class: infer
  print_interval: 10000
  init_model_path: "increment/9" # load model path

#train
phase:
- name: phase1
  model: "{workspace}/model.py" # user-defined model
  dataset_name: dataset_train # select dataset by name
  thread_num: 12

##offline infer
#phase:
#- name: phase1
#  model: "{workspace}/model.py" # user-defined model
#  dataset_name: dataset_infer # select dataset by name
#  save_path: "./infer_result"
#  thread_num: 1

##offline infer
#phase:
#- name: phase1
#  model: "{workspace}/model.py" # user-defined model
#  dataset_name: dataset_online_infer # select dataset by name
#  save_path: "./infer_result"
#  thread_num: 1