first commit

test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml

@@ -0,0 +1,122 @@
+Global:
+  use_gpu: True
+  epoch_num: &epoch_num 200
+  log_smooth_window: 10
+  print_batch_step: 10
+  save_model_dir: ./output/ser_layoutxlm_xfund_zh
+  save_epoch_step: 2000
+  # evaluation is run every 10 iterations after the 0th iteration
+  eval_batch_step: [ 0, 187 ]
+  cal_metric_during_train: False
+  save_inference_dir:
+  use_visualdl: False
+  seed: 2022
+  infer_img: ppstructure/docs/kie/input/zh_val_42.jpg
+  save_res_path: ./output/ser_layoutxlm_xfund_zh/res
+
+Architecture:
+  model_type: kie
+  algorithm: &algorithm "LayoutXLM"
+  Transform:
+  Backbone:
+    name: LayoutXLMForSer
+    pretrained: True
+    checkpoints: 
+    num_classes: &num_classes 7
+
+Loss:
+  name: VQASerTokenLayoutLMLoss
+  num_classes: *num_classes
+  key: "backbone_out"
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Linear
+    learning_rate: 0.00005
+    epochs: *epoch_num
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 0.00000
+    
+PostProcess:
+  name: VQASerTokenLayoutLMPostProcess
+  class_path: &class_path train_data/XFUND/class_list_xfun.txt
+
+Metric:
+  name: VQASerTokenMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_train/image
+    label_file_list: 
+      - train_data/XFUND/zh_train/train.json
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: False
+          algorithm: *algorithm
+          class_path: *class_path
+      - VQATokenPad:
+          max_seq_len: &max_seq_len 512
+          return_attention_mask: True
+      - VQASerTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 16
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_val/image
+    label_file_list:
+      - train_data/XFUND/zh_val/val.json
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: False
+          algorithm: *algorithm
+          class_path: *class_path
+      - VQATokenPad:
+          max_seq_len: *max_seq_len
+          return_attention_mask: True
+      - VQASerTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'image', 'labels'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4

test_tipc/configs/layoutxlm_ser/train_infer_python.txt

@@ -0,0 +1,59 @@
+===========================train_params===========================
+model_name:layoutxlm_ser
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=17
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=4|whole_train_whole_infer=8
+Architecture.Backbone.checkpoints:null
+train_model_name:latest
+train_infer_img_dir:ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o Global.print_batch_step=1 Global.eval_batch_step=[1000,1000] Train.loader.shuffle=false
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Architecture.Backbone.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:null
+infer_export:null
+infer_quant:False
+inference:ppstructure/kie/predict_kie_token_ser.py  --kie_algorithm=LayoutXLM  --ser_dict_path=train_data/XFUND/class_list_xfun.txt --output=output
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--ser_model_dir:
+--image_dir:./ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,224,224]}]
+===========================train_benchmark_params==========================
+batch_size:8
+fp_items:fp32|fp16
+epoch:3
+--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

test_tipc/configs/layoutxlm_ser/train_linux_gpu_fleet_normal_infer_python_linux_gpu_cpu.txt

@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:layoutxlm_ser
+python:python3.7
+gpu_list:192.168.0.1,192.168.0.2;0,1
+Global.use_gpu:True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=17
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=4|whole_train_whole_infer=8
+Architecture.Backbone.checkpoints:null
+train_model_name:latest
+train_infer_img_dir:ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Architecture.Backbone.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:null
+infer_export:null
+infer_quant:False
+inference:ppstructure/kie/predict_kie_token_ser.py  --kie_algorithm=LayoutXLM  --ser_dict_path=train_data/XFUND/class_list_xfun.txt --output=output
+--use_gpu:False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--ser_model_dir:
+--image_dir:./ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,224,224]}]

test_tipc/configs/layoutxlm_ser/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:layoutxlm_ser
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=17
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=4|whole_train_whole_infer=8
+Architecture.Backbone.checkpoints:null
+train_model_name:latest
+train_infer_img_dir:ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o Global.print_batch_step=1 Global.eval_batch_step=[1000,1000] Train.loader.shuffle=false
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Architecture.Backbone.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:null
+infer_export:null
+infer_quant:False
+inference:ppstructure/kie/predict_kie_token_ser.py  --kie_algorithm=LayoutXLM  --ser_dict_path=train_data/XFUND/class_list_xfun.txt --output=output
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--ser_model_dir:
+--image_dir:./ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,224,224]}]

test_tipc/configs/layoutxlm_ser/train_pact_infer_python.txt

@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:layoutxlm_ser_PACT
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=17
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=4|whole_train_whole_infer=8
+Architecture.Backbone.pretrained:pretrain_models/ser_LayoutXLM_xfun_zh
+train_model_name:latest
+train_infer_img_dir:ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+##
+trainer:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o Global.eval_batch_step=[2000,10]
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Architecture.Backbone.checkpoints:
+norm_export:null
+quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o 
+fpgm_export: null
+distill_export:null
+export1:null
+export2:null
+##
+infer_model:null
+infer_export:null
+infer_quant:False
+inference:ppstructure/kie/predict_kie_token_ser.py  --kie_algorithm=LayoutXLM  --ser_dict_path=train_data/XFUND/class_list_xfun.txt --output=output
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:fp32
+--ser_model_dir:
+--image_dir:./ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,224,224]}]

test_tipc/configs/layoutxlm_ser/train_ptq_infer_python.txt

@@ -0,0 +1,21 @@
+===========================train_params===========================
+model_name:layoutxlm_ser_KL
+python:python3.7
+Global.pretrained_model:
+Global.save_inference_dir:null
+infer_model:./inference/ser_LayoutXLM_xfun_zh_infer/
+infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/layoutxlm_ser/ser_layoutxlm_xfund_zh.yml -o Train.loader.batch_size_per_card=1 Eval.loader.batch_size_per_card=1
+infer_quant:True
+inference:ppstructure/kie/predict_kie_token_ser.py --kie_algorithm=LayoutXLM --ser_dict_path=./train_data/XFUND/class_list_xfun.txt
+--use_gpu:True|False
+--enable_mkldnn:False
+--cpu_threads:6
+--rec_batch_num:1
+--use_tensorrt:False
+--precision:int8
+--ser_model_dir:
+--image_dir:./ppstructure/docs/kie/input/zh_val_42.jpg
+null:null
+--benchmark:False
+null:null
+null:null