请问训练det_server模型时候可以使用混合精度？

[SonGohan757]

训练指令：
python -m paddle.distributed.launch --gpus "0,1" tools/train.py -c configs/det/ch_PP-OCRv4/627_server_config.yaml -o Global.use_amp=True Global.use_dynamic_loss_scaling=True
我的config(已经消除敏感信息):
Global:
debug: false
use_gpu: true
epoch_num: 300
log_smooth_window: 20
print_batch_step: 10
save_model_dir: output/627_cf_hz_tl
save_epoch_step: 1
eval_batch_step:

• 0
• 500
  cal_metric_during_train: false
  checkpoints: null
  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/ch_PP-OCRv4_det_server_trained.pdparams
  save_inference_dir: null
  use_visualdl: true
  distributed: true
  Architecture:
  model_type: det
  algorithm: DB
  Transform: null
  Backbone:
  name: PPHGNet_small
  det: true
  Neck:
  name: LKPAN
  out_channels: 256
  intracl: true
  Head:
  name: PFHeadLocal
  k: 50
  mode: large
  Loss:
  name: DBLoss
  balance_loss: true
  main_loss_type: DiceLoss
  alpha: 5
  beta: 10
  ohem_ratio: 3
  Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
  name: Cosine
  learning_rate: 0.00015
  warmup_epoch: 5
  regularizer:
  name: L2
  factor: 2e-6
  PostProcess:
  name: DBPostProcess
  thresh: 0.3
  box_thresh: 0.6
  max_candidates: 1000
  unclip_ratio: 2.0
  Metric:
  name: DetMetric
  main_indicator: hmean
  Train:
  dataset:
  name: TextDetDataset
  data_dir:
  label_file_list:
  transforms:
  • DecodeImage:
    img_mode: BGR
    channel_first: false
  • DetLabelEncode: null
  • CopyPaste: null

- IaaAugment:

augmenter_args:

- type: Fliplr

args:

p: 0.5

- type: Affine

args:

rotate:

- -10

- 10

- type: Resize

args:

size:

- 0.5

- 3

- EastRandomCropData:
    size:
    - 640
    - 640
    max_tries: 50
    keep_ratio: true
- MakeBorderMap:
    shrink_ratio: 0.4
    thresh_min: 0.3
    thresh_max: 0.7
    total_epoch: 500
- MakeShrinkMap:
    shrink_ratio: 0.4
    min_text_size: 8
    total_epoch: 500
- NormalizeImage:
    scale: 1./255.
    mean:
    - 0.485
    - 0.456
    - 0.406
    std:
    - 0.229
    - 0.224
    - 0.225
    order: hwc
- ToCHWImage: null
- KeepKeys:
    keep_keys:
    - image
    - threshold_map
    - threshold_mask
    - shrink_map
    - shrink_mask

loader:
shuffle: true
drop_last: true
batch_size_per_card: 8
num_workers: 2
use_shared_memory: false
Eval:
dataset:
name: TextDetDataset
data_dir:
label_file_list:
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- DetLabelEncode: null
- DetResizeForTest:
resize_long: 2560
- NormalizeImage:
scale: 1./255.
mean:
- 0.485
- 0.456
- 0.406
std:
- 0.229
- 0.224
- 0.225
order: hwc
- ToCHWImage: null
- KeepKeys:
keep_keys:
- image
- shape
- polys
- ignore_tags
loader:
shuffle: false
drop_last: false
batch_size_per_card: 1
num_workers: 2
profiler_options: null

[GreatV]

please refer to: https://github.com/PaddlePaddle/PaddleOCR/blob/main/doc/doc_en/detection_en.md#24-mixed-precision-training