mbv2_qat_dis.yaml

Distillation:
  distill_lambda: 1.0
  distill_loss: l2_loss
  distill_node_pair:
  - teacher_conv2d_54.tmp_0
  - conv2d_54.tmp_0
  - teacher_conv2d_55.tmp_0
  - conv2d_55.tmp_0
  - teacher_conv2d_57.tmp_0
  - conv2d_57.tmp_0
  - teacher_elementwise_add_0
  - elementwise_add_0
  - teacher_conv2d_61.tmp_0
  - conv2d_61.tmp_0
  - teacher_elementwise_add_1
  - elementwise_add_1
  - teacher_elementwise_add_2
  - elementwise_add_2
  - teacher_conv2d_67.tmp_0
  - conv2d_67.tmp_0
  - teacher_elementwise_add_3
  - elementwise_add_3
  - teacher_elementwise_add_4
  - elementwise_add_4
  - teacher_elementwise_add_5
  - elementwise_add_5
  - teacher_conv2d_75.tmp_0
  - conv2d_75.tmp_0
  - teacher_elementwise_add_6
  - elementwise_add_6
  - teacher_elementwise_add_7
  - elementwise_add_7
  - teacher_conv2d_81.tmp_0
  - conv2d_81.tmp_0
  - teacher_elementwise_add_8
  - elementwise_add_8
  - teacher_elementwise_add_9
  - elementwise_add_9
  - teacher_conv2d_87.tmp_0
  - conv2d_87.tmp_0
  - teacher_linear_1.tmp_0
  - linear_1.tmp_0
  merge_feed: true
  teacher_model_dir: ./infermodel_mobilenetv2
  teacher_model_filename: inference.pdmodel
  teacher_params_filename: inference.pdiparams
Quantization:
  activation_bits: 8
  is_full_quantize: false
  not_quant_pattern:
  - skip_quant
  quantize_op_types:
  - conv2d
  - depthwise_conv2d
  weight_bits: 8
TrainConfig:
  epochs: 1
  eval_iter: 1000
  learning_rate: 0.0001
  optimizer: SGD
  optim_args:
    weight_decay: 4.0e-05
  origin_metric: 0.765