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: "models/contentunderstanding/textcnn_pretrain"

dataset:
- name: dataset_train
  batch_size: 128
  type: DataLoader
  data_path: "{workspace}/senta_data/train"
  data_converter: "{workspace}/reader.py"
- name: dataset_infer
  batch_size: 256
  type: DataLoader
  data_path: "{workspace}/senta_data/test"
  data_converter: "{workspace}/reader.py"

hyper_parameters:
  optimizer:
    class: adam
    learning_rate: 0.001
    strategy: async

mode: [train_runner,infer_runner]

runner:
- name: train_runner
  class: train
  epochs: 6
  device: cpu
  save_checkpoint_interval: 1
  save_checkpoint_path: "increment"
  init_model_path: "" 
  print_interval: 10
  # startup class for finetuning
  startup_class_path: "{workspace}/finetune_startup.py"
  # path of pretrained model. Please set empty if you don't use finetune function.
  init_pretraining_model_path: "{workspace}/pretrain_model/pretrain_model_params"
 
  phases: phase_train

- name: infer_runner
  class: infer
  # device to run training or infer
  device: cpu
  print_interval: 1
  init_model_path: "increment/3" # load model path
  phases: phase_infer

  
phase:
- name: phase_train
  model: "{workspace}/model.py"
  dataset_name: dataset_train
  thread_num: 1
- name: phase_infer
  model: "{workspace}/model.py" # user-defined model
  dataset_name: dataset_infer # select dataset by name
  thread_num: 1