训练PGNET警告：使用PGNET训练自己的数据集时，重复got different data type, run type protmotion automatically, this may cause data type been changed.警告

[shrek-dior]

问题描述 / Problem Description

运行环境 / Runtime Environment

• OS:win11 cuda 12.5 cudnn 8.9.7.29
• Paddle:gpu 2.6.0（cuda12.0）
• PaddleOCR:2.7.3

配置文件

Global:
use_gpu: True
epoch_num: 600
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/pgnet_r50_vd_totaltext/
save_epoch_step: 10

evaluation is run every 0 iterationss after the 1000th iteration

eval_batch_step: [ 0, 1000 ]
cal_metric_during_train: False
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img:
infer_visual_type: EN # two mode: EN is for english datasets, CN is for chinese datasets
valid_set: partvgg # two mode: totaltext valid curved words, partvgg valid non-curved words
save_res_path: ./output/pgnet_r50_vd_totaltext/predicts_pgnet.txt
character_dict_path: ppocr/utils/ic15_dict.txt
character_type: EN
max_text_length: 50 # the max length in seq
max_text_nums: 30 # the max seq nums in a pic
tcl_len: 64

Architecture:
model_type: e2e
algorithm: PGNet
Transform:
Backbone:
name: ResNet
layers: 50
Neck:
name: PGFPN
Head:
name: PGHead
character_dict_path: ppocr/utils/ic15_dict.txt # the same as Global:character_dict_path

Loss:
name: PGLoss
tcl_bs: 64
max_text_length: 50 # the same as Global: max_text_length
max_text_nums: 30 # the same as Global：max_text_nums
pad_num: 36 # the length of dict for pad

Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 50
regularizer:
name: 'L2'
factor: 0.0001

PostProcess:
name: PGPostProcess
score_thresh: 0.5
mode: fast # fast or slow two ways
point_gather_mode: align # same as PGProcessTrain: point_gather_mode

Metric:
name: E2EMetric
mode: A # two ways for eval, A: label from txt, B: label from gt_mat
gt_mat_dir: ./train_data/total_text/gt # the dir of gt_mat
character_dict_path: ppocr/utils/ic15_dict.txt
main_indicator: f_score_e2e

Train:
dataset:
name: PGDataSet
data_dir: E:/Files/ocr/det/train
label_file_list: [E:/Files/ocr/det/train.txt]
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- E2ELabelEncodeTrain:
- PGProcessTrain:
batch_size: 6 # same as loader: batch_size_per_card
use_resize: True
use_random_crop: False
min_crop_size: 24
min_text_size: 4
max_text_size: 512
point_gather_mode: align # two mode: align and none, align mode is better than none mode
- KeepKeys:
keep_keys: [ 'images', 'tcl_maps', 'tcl_label_maps', 'border_maps','direction_maps', 'training_masks', 'label_list', 'pos_list', 'pos_mask' ] # dataloader will return list in this order
loader:
shuffle: True
drop_last: True
batch_size_per_card: 6
num_workers: 6

Eval:
dataset:
name: PGDataSet
data_dir: E:/Files/ocr/det/test
label_file_list: [E:/Files/ocr/det/test.txt]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- E2ELabelEncodeTest:
- E2EResizeForTest:
max_side_len: 768
- NormalizeImage:
scale: 1./255.
mean: [ 0.485, 0.456, 0.406 ]
std: [ 0.229, 0.224, 0.225 ]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: [ 'image', 'shape', 'polys', 'texts', 'ignore_tags', 'img_id']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2

完整报错 / Complete Error Message

W0708 10:27:34.562556 14708 dygraph_functions.cc:52641] got different data type, run type protmotion automatically, this may cause data type been changed.
W0708 10:27:34.562556 14708 dygraph_functions.cc:52641] got different data type, run type protmotion automatically, this may cause data type been changed.
W0708 10:27:35.342645 14708 dygraph_functions.cc:68148] got different data type, run type protmotion automatically, this may cause data type been changed.
W0708 10:27:35.343647 14708 multiply_fwd_func.cc:64] got different data type, run type protmotion automatically, this may cause data type been changed.
W0708 10:27:35.343647 14708 multiply_fwd_func.cc:64] got different data type, run type protmotion automatically, this may cause data type been changed.
W0708 10:27:35.343647 14708 multiply_fwd_func.cc:64] got different data type, run type protmotion automatically, this may cause data type been changed.
W0708 10:27:35.343647 14708 multiply_fwd_func.cc:64] got different data type, run type protmotion automatically, this may cause data type been changed.

运行命令行

python tools/train.py -c configs/e2e/e2e_r50_vd_pg.yml -o Global.pretrained_model=./pretrain_models/train_step1/best_accuracy Global.load_static_weights=False