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
workspace: "paddlerec.models.rank.flen"

# list of dataset
dataset:
- name: dataloader_train # name of dataset to distinguish different datasets
  batch_size: 2
  type: DataLoader # or QueueDataset 
  data_path: "{workspace}/data/sample_data/train"
  sparse_slots: "click user_0 user_1 user_2 user_3 user_4 user_5 user_6 user_7 user_8 user_9 user_10 user_11 item_0 item_1 item_2 contex_0 contex_1 contex_2 contex_3 contex_4 contex_5"
  dense_slots: ""
- name: dataset_infer # name
  batch_size: 2
  type: DataLoader # or QueueDataset
  data_path: "{workspace}/data/sample_data/train"
  sparse_slots: "click user_0 user_1 user_2 user_3 user_4 user_5 user_6 user_7 user_8 user_9 user_10 user_11 item_0 item_1 item_2 contex_0 contex_1 contex_2 contex_3 contex_4 contex_5"
  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_inputs_slots: 21
  sparse_feature_number: 100
  sparse_feature_dim: 8
  dense_input_dim: 1
  dropout_rate: 0.5

# select runner by name
mode: [single_cpu_train, single_cpu_infer]
# config of each runner.
# runner is a kind of paddle training class, which wraps the train/infer process.
runner:
- name: single_cpu_train
  class: train
  # num of epochs
  epochs: 1
  # device to run training or infer
  device: cpu
  save_checkpoint_interval: 1 # save model interval of epochs
  save_inference_interval: 4 # save inference
  save_checkpoint_path: "increment_model" # save checkpoint path
  save_inference_path: "inference" # save inference path
  save_inference_feed_varnames: [] # feed vars of save inference
  save_inference_fetch_varnames: [] # fetch vars of save inference
  init_model_path: "" # load model path
  print_interval: 2
  phases: [phase1]

- name: single_gpu_train
  class: train
  # num of epochs
  epochs: 1
  # device to run training or infer
  device: gpu
  save_checkpoint_interval: 1 # save model interval of epochs
  save_inference_interval: 4 # save inference
  save_checkpoint_path: "increment_model" # save checkpoint path
  save_inference_path: "inference" # save inference path
  save_inference_feed_varnames: [] # feed vars of save inference
  save_inference_fetch_varnames: [] # fetch vars of save inference
  init_model_path: "" # load model path
  print_interval: 2
  phases: [phase1]

- name: single_cpu_infer
  class: infer
  # device to run training or infer
  device: cpu
  init_model_path: "increment_model" # load model path
  phases: [phase2]

- name: single_gpu_infer
  class: infer
  # device to run training or infer
  device: gpu
  init_model_path: "increment_model" # load model path
  phases: [phase2]

# runner will run all the phase in each epoch
phase:
- name: phase1
  model: "{workspace}/model.py" # user-defined model
  dataset_name: dataloader_train # select dataset by name
  thread_num: 2

- name: phase2
  model: "{workspace}/model.py" # user-defined model
  dataset_name: dataset_infer # select dataset by name
  thread_num: 2