first commit

test_tipc/configs/rec_parseq/rec_vit_parseq.yml

@@ -0,0 +1,118 @@
+Global:
+  use_gpu: True
+  epoch_num: 20
+  log_smooth_window: 20
+  print_batch_step: 5
+  save_model_dir: ./output/rec/parseq
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 500]
+  cal_metric_during_train: True
+  pretrained_model: 
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path:
+  character_type: en
+  max_text_length: 25
+  num_heads: 8
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_parseq.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: OneCycle
+    max_lr: 0.0007
+
+Architecture:
+  model_type: rec
+  algorithm: ParseQ
+  in_channels: 3
+  Transform:
+  Backbone:
+    name: ViTParseQ
+    img_size: [32, 128]
+    patch_size: [4, 8]
+    embed_dim: 384
+    depth: 12
+    num_heads: 6
+    mlp_ratio: 4
+    in_channels: 3
+  Head:
+    name: ParseQHead
+    # Architecture
+    max_text_length: 25
+    embed_dim: 384
+    dec_num_heads: 12
+    dec_mlp_ratio: 4
+    dec_depth: 1
+    # Training
+    perm_num: 6
+    perm_forward: true
+    perm_mirrored: true
+    dropout: 0.1
+    # Decoding mode (test)
+    decode_ar: true
+    refine_iters: 1
+
+Loss:
+  name: ParseQLoss
+
+PostProcess:
+  name: ParseQLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  is_filter: True
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data/
+    label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ParseQRecAug:
+          aug_type: 0 # or 1
+      - ParseQLabelEncode:
+      - SVTRRecResizeImg:
+          image_shape: [3, 32, 128]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 192
+    drop_last: True
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ic15_data
+    label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - ParseQLabelEncode: # Class handling label
+      - SVTRRecResizeImg:
+          image_shape: [3, 32, 128]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] 
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 384
+    num_workers: 4

test_tipc/configs/rec_parseq/train_infer_python.txt

@@ -0,0 +1,61 @@
+===========================train_params===========================
+model_name:rec_parseq
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:null
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=64
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/rec_parseq/rec_vit_parseq.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c test_tipc/configs/rec_parseq/rec_vit_parseq.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/rec_parseq/rec_vit_parseq.yml -o
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+train_model:./inference/rec_parseq_train/best_accuracy
+infer_export:tools/export_model.py -c test_tipc/configs/rec_parseq/rec_vit_parseq.yml -o
+infer_quant:False
+inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,128" --rec_algorithm="ParseQ"
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,128]}]
+===========================train_benchmark_params==========================
+batch_size:512
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
+===========================to_static_train_benchmark_params===========================
+to_static_train:Global.to_static=true