diff --git a/ppocr/postprocess/east_postprocess.py b/ppocr/postprocess/east_postprocess.py index ceee727aa3df052041aee925c6c856773c8a288e..ec6bf663854d3391bf8c584aa749dc6d1805d344 100755 --- a/ppocr/postprocess/east_postprocess.py +++ b/ppocr/postprocess/east_postprocess.py @@ -20,6 +20,7 @@ import numpy as np from .locality_aware_nms import nms_locality import cv2 import paddle +import lanms import os import sys @@ -29,6 +30,7 @@ class EASTPostProcess(object): """ The post process for EAST. """ + def __init__(self, score_thresh=0.8, cover_thresh=0.1, @@ -38,11 +40,6 @@ class EASTPostProcess(object): self.score_thresh = score_thresh self.cover_thresh = cover_thresh self.nms_thresh = nms_thresh - - # c++ la-nms is faster, but only support python 3.5 - self.is_python35 = False - if sys.version_info.major == 3 and sys.version_info.minor == 5: - self.is_python35 = True def restore_rectangle_quad(self, origin, geometry): """ @@ -79,11 +76,8 @@ class EASTPostProcess(object): boxes = np.zeros((text_box_restored.shape[0], 9), dtype=np.float32) boxes[:, :8] = text_box_restored.reshape((-1, 8)) boxes[:, 8] = score_map[xy_text[:, 0], xy_text[:, 1]] - if self.is_python35: - import lanms - boxes = lanms.merge_quadrangle_n9(boxes, nms_thresh) - else: - boxes = nms_locality(boxes.astype(np.float64), nms_thresh) + boxes = lanms.merge_quadrangle_n9(boxes, nms_thresh) + # boxes = nms_locality(boxes.astype(np.float64), nms_thresh) if boxes.shape[0] == 0: return [] # Here we filter some low score boxes by the average score map, @@ -139,4 +133,4 @@ class EASTPostProcess(object): continue boxes_norm.append(box) dt_boxes_list.append({'points': np.array(boxes_norm)}) - return dt_boxes_list \ No newline at end of file + return dt_boxes_list diff --git a/requirements.txt b/requirements.txt index 0c87c5c95069a2699f5a3a50320c883c6118ffe7..903b8eda055573621f5d5479e85b17986b702ead 100644 --- a/requirements.txt +++ b/requirements.txt @@ -12,4 +12,5 @@ cython lxml premailer openpyxl -fasttext==0.9.1 \ No newline at end of file +fasttext==0.9.1 +lanms-nova \ No newline at end of file diff --git a/test_tipc/configs/det_mv3_east_v2.0/det_mv3_east.yml b/test_tipc/configs/det_mv3_east_v2.0/det_mv3_east.yml new file mode 100644 index 0000000000000000000000000000000000000000..4ae32ab004684f040b5939be7f348d468b4b8024 --- /dev/null +++ b/test_tipc/configs/det_mv3_east_v2.0/det_mv3_east.yml @@ -0,0 +1,109 @@ +Global: + use_gpu: true + epoch_num: 10000 + log_smooth_window: 20 + print_batch_step: 2 + save_model_dir: ./output/east_mv3/ + save_epoch_step: 1000 + # evaluation is run every 5000 iterations after the 4000th iteration + eval_batch_step: [4000, 5000] + cal_metric_during_train: False + pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained + checkpoints: + save_inference_dir: + use_visualdl: False + infer_img: + save_res_path: ./output/det_east/predicts_east.txt + +Architecture: + model_type: det + algorithm: EAST + Transform: + Backbone: + name: MobileNetV3 + scale: 0.5 + model_name: large + Neck: + name: EASTFPN + model_name: small + Head: + name: EASTHead + model_name: small + +Loss: + name: EASTLoss + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + # name: Cosine + learning_rate: 0.001 + # warmup_epoch: 0 + regularizer: + name: 'L2' + factor: 0 + +PostProcess: + name: EASTPostProcess + score_thresh: 0.8 + cover_thresh: 0.1 + nms_thresh: 0.2 + +Metric: + name: DetMetric + main_indicator: hmean + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/icdar2015/text_localization/ + label_file_list: + - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt + ratio_list: [1.0] + transforms: + - DecodeImage: # load image + img_mode: BGR + channel_first: False + - DetLabelEncode: # Class handling label + - EASTProcessTrain: + image_shape: [512, 512] + background_ratio: 0.125 + min_crop_side_ratio: 0.1 + min_text_size: 10 + - KeepKeys: + keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order + loader: + shuffle: True + drop_last: False + batch_size_per_card: 16 + num_workers: 8 + +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data/icdar2015/text_localization/ + label_file_list: + - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt + transforms: + - DecodeImage: # load image + img_mode: BGR + channel_first: False + - DetLabelEncode: # Class handling label + - DetResizeForTest: + limit_side_len: 2400 + limit_type: max + - 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', 'ignore_tags'] + loader: + shuffle: False + drop_last: False + batch_size_per_card: 1 # must be 1 + num_workers: 2 \ No newline at end of file diff --git a/test_tipc/configs/det_mv3_east_v2.0/train_infer_python.txt b/test_tipc/configs/det_mv3_east_v2.0/train_infer_python.txt new file mode 100644 index 0000000000000000000000000000000000000000..7a3aced57aaf31bb54075d8ba3119d1626a2c58a --- /dev/null +++ b/test_tipc/configs/det_mv3_east_v2.0/train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:det_mv3_east_v2.0 +python:python3.7 +gpu_list:0 +Global.use_gpu:True|True +Global.auto_cast:fp32 +Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500 +Global.save_model_dir:./output/ +Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4 +Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/ +null:null +## +trainer:norm_train +norm_train:tools/train.py -c test_tipc/configs/det_mv3_east_v2.0/det_mv3_east.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/ +Global.pretrained_model: +norm_export:tools/export_model.py -c test_tipc/configs/det_mv3_east_v2.0/det_mv3_east.yml -o +quant_export:null +fpgm_export:null +distill_export:null +export1:null +export2:null +## +train_model:./inference/det_mv3_east/best_accuracy +infer_export:tools/export_model.py -c test_tipc/cconfigs/det_mv3_east_v2.0/det_mv3_east.yml -o +infer_quant:False +inference:tools/infer/predict_det.py +--use_gpu:True|False +--enable_mkldnn:True|False +--cpu_threads:1|6 +--rec_batch_num:1 +--use_tensorrt:False|True +--precision:fp32|fp16|int8 +--det_model_dir: +--image_dir:./inference/ch_det_data_50/all-sum-510/ +--save_log_path:null +--benchmark:True +--det_algorithm:EAST diff --git a/test_tipc/configs/det_r50_vd_east_v2.0/det_r50_vd_east.yml b/test_tipc/configs/det_r50_vd_east_v2.0/det_r50_vd_east.yml new file mode 100644 index 0000000000000000000000000000000000000000..c6b6fc3ed79d0d717fe3dbd4cb9c8559ff8f07c4 --- /dev/null +++ b/test_tipc/configs/det_r50_vd_east_v2.0/det_r50_vd_east.yml @@ -0,0 +1,108 @@ +Global: + use_gpu: true + epoch_num: 10000 + log_smooth_window: 20 + print_batch_step: 2 + save_model_dir: ./output/east_r50_vd/ + save_epoch_step: 1000 + # evaluation is run every 5000 iterations after the 4000th iteration + eval_batch_step: [4000, 5000] + cal_metric_during_train: False + pretrained_model: + checkpoints: + save_inference_dir: + use_visualdl: False + infer_img: + save_res_path: ./output/det_east/predicts_east.txt + +Architecture: + model_type: det + algorithm: EAST + Transform: + Backbone: + name: ResNet + layers: 50 + Neck: + name: EASTFPN + model_name: large + Head: + name: EASTHead + model_name: large + +Loss: + name: EASTLoss + +Optimizer: + name: Adam + beta1: 0.9 + beta2: 0.999 + lr: + # name: Cosine + learning_rate: 0.001 + # warmup_epoch: 0 + regularizer: + name: 'L2' + factor: 0 + +PostProcess: + name: EASTPostProcess + score_thresh: 0.8 + cover_thresh: 0.1 + nms_thresh: 0.2 + +Metric: + name: DetMetric + main_indicator: hmean + +Train: + dataset: + name: SimpleDataSet + data_dir: ./train_data/icdar2015/text_localization/ + label_file_list: + - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt + ratio_list: [1.0] + transforms: + - DecodeImage: # load image + img_mode: BGR + channel_first: False + - DetLabelEncode: # Class handling label + - EASTProcessTrain: + image_shape: [512, 512] + background_ratio: 0.125 + min_crop_side_ratio: 0.1 + min_text_size: 10 + - KeepKeys: + keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order + loader: + shuffle: True + drop_last: False + batch_size_per_card: 8 + num_workers: 8 + +Eval: + dataset: + name: SimpleDataSet + data_dir: ./train_data/icdar2015/text_localization/ + label_file_list: + - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt + transforms: + - DecodeImage: # load image + Fa: BGR + channel_first: False + - DetLabelEncode: # Class handling label + - DetResizeForTest: + limit_side_len: 2400 + limit_type: max + - 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', 'ignore_tags'] + loader: + shuffle: False + drop_last: False + batch_size_per_card: 1 # must be 1 + num_workers: 2 \ No newline at end of file diff --git a/test_tipc/configs/det_r50_vd_east_v2.0/train_infer_python.txt b/test_tipc/configs/det_r50_vd_east_v2.0/train_infer_python.txt new file mode 100644 index 0000000000000000000000000000000000000000..e9eaa779520f78622509153482fd6a84322c9cc5 --- /dev/null +++ b/test_tipc/configs/det_r50_vd_east_v2.0/train_infer_python.txt @@ -0,0 +1,51 @@ +===========================train_params=========================== +model_name:det_r50_vd_east_v2.0 +python:python3.7 +gpu_list:0 +Global.use_gpu:True|True +Global.auto_cast:fp32 +Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500 +Global.save_model_dir:./output/ +Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4 +Global.pretrained_model:null +train_model_name:latest +train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/ +null:null +## +trainer:norm_train +norm_train:tools/train.py -c test_tipc/configs/det_r50_vd_east_v2.0/det_r50_vd_east.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/ +Global.pretrained_model: +norm_export:tools/export_model.py -c test_tipc/configs/det_r50_vd_east_v2.0/det_r50_vd_east.yml -o +quant_export:null +fpgm_export:null +distill_export:null +export1:null +export2:null +## +train_model:./inference/det_mv3_east/best_accuracy +infer_export:tools/export_model.py -c test_tipc/cconfigs/det_r50_vd_east_v2.0/det_r50_vd_east.yml -o +infer_quant:False +inference:tools/infer/predict_det.py +--use_gpu:True|False +--enable_mkldnn:True|False +--cpu_threads:1|6 +--rec_batch_num:1 +--use_tensorrt:False|True +--precision:fp32|fp16|int8 +--det_model_dir: +--image_dir:./inference/ch_det_data_50/all-sum-510/ +--save_log_path:null +--benchmark:True +--det_algorithm:EAST