utility.py 22.4 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import argparse
import os
import sys
import platform
import cv2
import numpy as np
import paddle
from PIL import Image, ImageDraw, ImageFont
import math
from paddle import inference
import time
from ppocr.utils.logging import get_logger


def str2bool(v):
    return v.lower() in ("true", "t", "1")


def init_args():
    parser = argparse.ArgumentParser()
    # params for prediction engine
    parser.add_argument("--use_gpu", type=str2bool, default=True)
    parser.add_argument("--use_xpu", type=str2bool, default=False)
    parser.add_argument("--ir_optim", type=str2bool, default=True)
    parser.add_argument("--use_tensorrt", type=str2bool, default=False)
    parser.add_argument("--min_subgraph_size", type=int, default=15)
    parser.add_argument("--shape_info_filename", type=str, default=None)
    parser.add_argument("--precision", type=str, default="fp32")
    parser.add_argument("--gpu_mem", type=int, default=500)

    # params for text detector
    parser.add_argument("--image_dir", type=str)
    parser.add_argument("--det_algorithm", type=str, default='DB')
    parser.add_argument("--det_model_dir", type=str)
    parser.add_argument("--det_limit_side_len", type=float, default=960)
    parser.add_argument("--det_limit_type", type=str, default='max')

    # DB parmas
    parser.add_argument("--det_db_thresh", type=float, default=0.3)
    parser.add_argument("--det_db_box_thresh", type=float, default=0.6)
    parser.add_argument("--det_db_unclip_ratio", type=float, default=1.5)
    parser.add_argument("--max_batch_size", type=int, default=10)
    parser.add_argument("--use_dilation", type=str2bool, default=False)
    parser.add_argument("--det_db_score_mode", type=str, default="fast")
    # EAST parmas
    parser.add_argument("--det_east_score_thresh", type=float, default=0.8)
    parser.add_argument("--det_east_cover_thresh", type=float, default=0.1)
    parser.add_argument("--det_east_nms_thresh", type=float, default=0.2)

    # SAST parmas
    parser.add_argument("--det_sast_score_thresh", type=float, default=0.5)
    parser.add_argument("--det_sast_nms_thresh", type=float, default=0.2)
    parser.add_argument("--det_sast_polygon", type=str2bool, default=False)

    # PSE parmas
    parser.add_argument("--det_pse_thresh", type=float, default=0)
    parser.add_argument("--det_pse_box_thresh", type=float, default=0.85)
    parser.add_argument("--det_pse_min_area", type=float, default=16)
    parser.add_argument("--det_pse_box_type", type=str, default='quad')
    parser.add_argument("--det_pse_scale", type=int, default=1)

    # FCE parmas
    parser.add_argument("--scales", type=list, default=[8, 16, 32])
    parser.add_argument("--alpha", type=float, default=1.0)
    parser.add_argument("--beta", type=float, default=1.0)
    parser.add_argument("--fourier_degree", type=int, default=5)
    parser.add_argument("--det_fce_box_type", type=str, default='poly')

    # params for text recognizer
    parser.add_argument("--rec_algorithm", type=str, default='SVTR_LCNet')
    parser.add_argument("--rec_model_dir", type=str)
    parser.add_argument("--rec_image_shape", type=str, default="3, 48, 320")
    parser.add_argument("--rec_batch_num", type=int, default=6)
    parser.add_argument("--max_text_length", type=int, default=25)
    parser.add_argument(
        "--rec_char_dict_path",
        type=str,
        default="./ppocr/utils/ppocr_keys_v1.txt")
    parser.add_argument("--use_space_char", type=str2bool, default=True)
    parser.add_argument(
        "--vis_font_path", type=str, default="./doc/fonts/simfang.ttf")
    parser.add_argument("--drop_score", type=float, default=0.5)

    # params for e2e
    parser.add_argument("--e2e_algorithm", type=str, default='PGNet')
    parser.add_argument("--e2e_model_dir", type=str)
    parser.add_argument("--e2e_limit_side_len", type=float, default=768)
    parser.add_argument("--e2e_limit_type", type=str, default='max')

    # PGNet parmas
    parser.add_argument("--e2e_pgnet_score_thresh", type=float, default=0.5)
    parser.add_argument(
        "--e2e_char_dict_path", type=str, default="./ppocr/utils/ic15_dict.txt")
    parser.add_argument("--e2e_pgnet_valid_set", type=str, default='totaltext')
    parser.add_argument("--e2e_pgnet_mode", type=str, default='fast')

    # params for text classifier
    parser.add_argument("--use_angle_cls", type=str2bool, default=False)
    parser.add_argument("--cls_model_dir", type=str)
    parser.add_argument("--cls_image_shape", type=str, default="3, 48, 192")
    parser.add_argument("--label_list", type=list, default=['0', '180'])
    parser.add_argument("--cls_batch_num", type=int, default=6)
    parser.add_argument("--cls_thresh", type=float, default=0.9)

    parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
    parser.add_argument("--cpu_threads", type=int, default=10)
    parser.add_argument("--use_pdserving", type=str2bool, default=False)
    parser.add_argument("--warmup", type=str2bool, default=False)

    # SR parmas
    parser.add_argument("--sr_model_dir", type=str)
    parser.add_argument("--sr_image_shape", type=str, default="3, 32, 128")
    parser.add_argument("--sr_batch_num", type=int, default=1)

    #
    parser.add_argument(
        "--draw_img_save_dir", type=str, default="./inference_results")
    parser.add_argument("--save_crop_res", type=str2bool, default=False)
    parser.add_argument("--crop_res_save_dir", type=str, default="./output")

    # multi-process
    parser.add_argument("--use_mp", type=str2bool, default=False)
    parser.add_argument("--total_process_num", type=int, default=1)
    parser.add_argument("--process_id", type=int, default=0)

    parser.add_argument("--benchmark", type=str2bool, default=False)
    parser.add_argument("--save_log_path", type=str, default="./log_output/")

    parser.add_argument("--show_log", type=str2bool, default=True)
    parser.add_argument("--use_onnx", type=str2bool, default=False)
    return parser


def parse_args():
    parser = init_args()
    return parser.parse_args()


def create_predictor(args, mode, logger):
    if mode == "det":
        model_dir = args.det_model_dir
    elif mode == 'cls':
        model_dir = args.cls_model_dir
    elif mode == 'rec':
        model_dir = args.rec_model_dir
    elif mode == 'table':
        model_dir = args.table_model_dir
    elif mode == 'ser':
        model_dir = args.ser_model_dir
    elif mode == "sr":
        model_dir = args.sr_model_dir
    elif mode == 'layout':
        model_dir = args.layout_model_dir
    else:
        model_dir = args.e2e_model_dir

    if model_dir is None:
        logger.info("not find {} model file path {}".format(mode, model_dir))
        sys.exit(0)
    if args.use_onnx:
        import onnxruntime as ort
        model_file_path = model_dir
        if not os.path.exists(model_file_path):
            raise ValueError("not find model file path {}".format(
                model_file_path))
        sess = ort.InferenceSession(model_file_path)
        return sess, sess.get_inputs()[0], None, None

    else:
        model_file_path = model_dir + "/inference.pdmodel"
        params_file_path = model_dir + "/inference.pdiparams"
        if not os.path.exists(model_file_path):
            raise ValueError("not find model file path {}".format(
                model_file_path))
        if not os.path.exists(params_file_path):
            raise ValueError("not find params file path {}".format(
                params_file_path))

        config = inference.Config(model_file_path, params_file_path)

        if hasattr(args, 'precision'):
            if args.precision == "fp16" and args.use_tensorrt:
                precision = inference.PrecisionType.Half
            elif args.precision == "int8":
                precision = inference.PrecisionType.Int8
            else:
                precision = inference.PrecisionType.Float32
        else:
            precision = inference.PrecisionType.Float32

        if args.use_gpu:
            gpu_id = get_infer_gpuid()
            if gpu_id is None:
                logger.warning(
                    "GPU is not found in current device by nvidia-smi. Please check your device or ignore it if run on jetson."
                )
            config.enable_use_gpu(args.gpu_mem, 0)
            if args.use_tensorrt:
                config.enable_tensorrt_engine(
                    workspace_size=1 << 30,
                    precision_mode=precision,
                    max_batch_size=args.max_batch_size,
                    min_subgraph_size=args.
                    min_subgraph_size,  # skip the minmum trt subgraph
                    use_calib_mode=False)

            # collect shape
            if args.shape_info_filename is not None:
                if not os.path.exists(args.shape_info_filename):
                    config.collect_shape_range_info(args.shape_info_filename)
                    logger.info(
                        f"collect dynamic shape info into : {args.shape_info_filename}"
                    )
                else:
                    logger.info(
                        f"dynamic shape info file( {args.shape_info_filename} ) already exists, not need to generate again."
                    )
                config.enable_tuned_tensorrt_dynamic_shape(
                    args.shape_info_filename, True)
            else:
                logger.info(
                    f"when using tensorrt, dynamic shape is a suggested option, you can use '--shape_info_filename=shape.txt' for offline dygnamic shape tuning"
                )

        elif args.use_xpu:
            config.enable_xpu(10 * 1024 * 1024)
        else:
            config.disable_gpu()
            if hasattr(args, "cpu_threads"):
                config.set_cpu_math_library_num_threads(args.cpu_threads)
            else:
                # default cpu threads as 10
                config.set_cpu_math_library_num_threads(10)
            if args.enable_mkldnn:
                # cache 10 different shapes for mkldnn to avoid memory leak
                config.set_mkldnn_cache_capacity(10)
                config.enable_mkldnn()
                if args.precision == "fp16":
                    config.enable_mkldnn_bfloat16()
        # enable memory optim
        config.enable_memory_optim()
        config.disable_glog_info()
        config.delete_pass("conv_transpose_eltwiseadd_bn_fuse_pass")
        config.delete_pass("matmul_transpose_reshape_fuse_pass")
        if mode == 'table':
            config.delete_pass("fc_fuse_pass")  # not supported for table
        config.switch_use_feed_fetch_ops(False)
        config.switch_ir_optim(True)

        # create predictor
        predictor = inference.create_predictor(config)
        input_names = predictor.get_input_names()
        if mode in ['ser', 're']:
            input_tensor = []
            for name in input_names:
                input_tensor.append(predictor.get_input_handle(name))
        else:
            for name in input_names:
                input_tensor = predictor.get_input_handle(name)
        output_tensors = get_output_tensors(args, mode, predictor)
        return predictor, input_tensor, output_tensors, config


def get_output_tensors(args, mode, predictor):
    output_names = predictor.get_output_names()
    output_tensors = []
    if mode == "rec" and args.rec_algorithm in ["CRNN", "SVTR_LCNet"]:
        output_name = 'softmax_0.tmp_0'
        if output_name in output_names:
            return [predictor.get_output_handle(output_name)]
        else:
            for output_name in output_names:
                output_tensor = predictor.get_output_handle(output_name)
                output_tensors.append(output_tensor)
    else:
        for output_name in output_names:
            output_tensor = predictor.get_output_handle(output_name)
            output_tensors.append(output_tensor)
    return output_tensors


def get_infer_gpuid():
    sysstr = platform.system()
    if sysstr == "Windows":
        return 0

    if not paddle.fluid.core.is_compiled_with_rocm():
        cmd = "env | grep CUDA_VISIBLE_DEVICES"
    else:
        cmd = "env | grep HIP_VISIBLE_DEVICES"
    env_cuda = os.popen(cmd).readlines()
    if len(env_cuda) == 0:
        return 0
    else:
        gpu_id = env_cuda[0].strip().split("=")[1]
        return int(gpu_id[0])


def draw_e2e_res(dt_boxes, strs, img_path):
    src_im = cv2.imread(img_path)
    for box, str in zip(dt_boxes, strs):
        box = box.astype(np.int32).reshape((-1, 1, 2))
        cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
        cv2.putText(
            src_im,
            str,
            org=(int(box[0, 0, 0]), int(box[0, 0, 1])),
            fontFace=cv2.FONT_HERSHEY_COMPLEX,
            fontScale=0.7,
            color=(0, 255, 0),
            thickness=1)
    return src_im


def draw_text_det_res(dt_boxes, img_path):
    src_im = cv2.imread(img_path)
    for box in dt_boxes:
        box = np.array(box).astype(np.int32).reshape(-1, 2)
        cv2.polylines(src_im, [box], True, color=(255, 255, 0), thickness=2)
    return src_im


def resize_img(img, input_size=600):
    """
    resize img and limit the longest side of the image to input_size
    """
    img = np.array(img)
    im_shape = img.shape
    im_size_max = np.max(im_shape[0:2])
    im_scale = float(input_size) / float(im_size_max)
    img = cv2.resize(img, None, None, fx=im_scale, fy=im_scale)
    return img


def draw_ocr(image,
             boxes,
             txts=None,
             scores=None,
             drop_score=0.5,
             font_path="./doc/fonts/simfang.ttf"):
    """
    Visualize the results of OCR detection and recognition
    args:
        image(Image|array): RGB image
        boxes(list): boxes with shape(N, 4, 2)
        txts(list): the texts
        scores(list): txxs corresponding scores
        drop_score(float): only scores greater than drop_threshold will be visualized
        font_path: the path of font which is used to draw text
    return(array):
        the visualized img
    """
    if scores is None:
        scores = [1] * len(boxes)
    box_num = len(boxes)
    for i in range(box_num):
        if scores is not None and (scores[i] < drop_score or
                                   math.isnan(scores[i])):
            continue
        box = np.reshape(np.array(boxes[i]), [-1, 1, 2]).astype(np.int64)
        image = cv2.polylines(np.array(image), [box], True, (255, 0, 0), 2)
    if txts is not None:
        img = np.array(resize_img(image, input_size=600))
        txt_img = text_visual(
            txts,
            scores,
            img_h=img.shape[0],
            img_w=600,
            threshold=drop_score,
            font_path=font_path)
        img = np.concatenate([np.array(img), np.array(txt_img)], axis=1)
        return img
    return image


def draw_ocr_box_txt(image,
                     boxes,
                     txts,
                     scores=None,
                     drop_score=0.5,
                     font_path="./doc/simfang.ttf"):
    h, w = image.height, image.width
    img_left = image.copy()
    img_right = Image.new('RGB', (w, h), (255, 255, 255))

    import random

    random.seed(0)
    draw_left = ImageDraw.Draw(img_left)
    draw_right = ImageDraw.Draw(img_right)
    for idx, (box, txt) in enumerate(zip(boxes, txts)):
        if scores is not None and scores[idx] < drop_score:
            continue
        color = (random.randint(0, 255), random.randint(0, 255),
                 random.randint(0, 255))
        draw_left.polygon(box, fill=color)
        draw_right.polygon(
            [
                box[0][0], box[0][1], box[1][0], box[1][1], box[2][0],
                box[2][1], box[3][0], box[3][1]
            ],
            outline=color)
        box_height = math.sqrt((box[0][0] - box[3][0])**2 + (box[0][1] - box[3][
            1])**2)
        box_width = math.sqrt((box[0][0] - box[1][0])**2 + (box[0][1] - box[1][
            1])**2)
        if box_height > 2 * box_width:
            font_size = max(int(box_width * 0.9), 10)
            font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
            cur_y = box[0][1]
            for c in txt:
                char_size = font.getsize(c)
                draw_right.text(
                    (box[0][0] + 3, cur_y), c, fill=(0, 0, 0), font=font)
                cur_y += char_size[1]
        else:
            font_size = max(int(box_height * 0.8), 10)
            font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
            draw_right.text(
                [box[0][0], box[0][1]], txt, fill=(0, 0, 0), font=font)
    img_left = Image.blend(image, img_left, 0.5)
    img_show = Image.new('RGB', (w * 2, h), (255, 255, 255))
    img_show.paste(img_left, (0, 0, w, h))
    img_show.paste(img_right, (w, 0, w * 2, h))
    return np.array(img_show)


def str_count(s):
    """
    Count the number of Chinese characters,
    a single English character and a single number
    equal to half the length of Chinese characters.
    args:
        s(string): the input of string
    return(int):
        the number of Chinese characters
    """
    import string
    count_zh = count_pu = 0
    s_len = len(s)
    en_dg_count = 0
    for c in s:
        if c in string.ascii_letters or c.isdigit() or c.isspace():
            en_dg_count += 1
        elif c.isalpha():
            count_zh += 1
        else:
            count_pu += 1
    return s_len - math.ceil(en_dg_count / 2)


def text_visual(texts,
                scores,
                img_h=400,
                img_w=600,
                threshold=0.,
                font_path="./doc/simfang.ttf"):
    """
    create new blank img and draw txt on it
    args:
        texts(list): the text will be draw
        scores(list|None): corresponding score of each txt
        img_h(int): the height of blank img
        img_w(int): the width of blank img
        font_path: the path of font which is used to draw text
    return(array):
    """
    if scores is not None:
        assert len(texts) == len(
            scores), "The number of txts and corresponding scores must match"

    def create_blank_img():
        blank_img = np.ones(shape=[img_h, img_w], dtype=np.int8) * 255
        blank_img[:, img_w - 1:] = 0
        blank_img = Image.fromarray(blank_img).convert("RGB")
        draw_txt = ImageDraw.Draw(blank_img)
        return blank_img, draw_txt

    blank_img, draw_txt = create_blank_img()

    font_size = 20
    txt_color = (0, 0, 0)
    font = ImageFont.truetype(font_path, font_size, encoding="utf-8")

    gap = font_size + 5
    txt_img_list = []
    count, index = 1, 0
    for idx, txt in enumerate(texts):
        index += 1
        if scores[idx] < threshold or math.isnan(scores[idx]):
            index -= 1
            continue
        first_line = True
        while str_count(txt) >= img_w // font_size - 4:
            tmp = txt
            txt = tmp[:img_w // font_size - 4]
            if first_line:
                new_txt = str(index) + ': ' + txt
                first_line = False
            else:
                new_txt = '    ' + txt
            draw_txt.text((0, gap * count), new_txt, txt_color, font=font)
            txt = tmp[img_w // font_size - 4:]
            if count >= img_h // gap - 1:
                txt_img_list.append(np.array(blank_img))
                blank_img, draw_txt = create_blank_img()
                count = 0
            count += 1
        if first_line:
            new_txt = str(index) + ': ' + txt + '   ' + '%.3f' % (scores[idx])
        else:
            new_txt = "  " + txt + "  " + '%.3f' % (scores[idx])
        draw_txt.text((0, gap * count), new_txt, txt_color, font=font)
        # whether add new blank img or not
        if count >= img_h // gap - 1 and idx + 1 < len(texts):
            txt_img_list.append(np.array(blank_img))
            blank_img, draw_txt = create_blank_img()
            count = 0
        count += 1
    txt_img_list.append(np.array(blank_img))
    if len(txt_img_list) == 1:
        blank_img = np.array(txt_img_list[0])
    else:
        blank_img = np.concatenate(txt_img_list, axis=1)
    return np.array(blank_img)


def base64_to_cv2(b64str):
    import base64
    data = base64.b64decode(b64str.encode('utf8'))
    data = np.fromstring(data, np.uint8)
    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
    return data


def draw_boxes(image, boxes, scores=None, drop_score=0.5):
    if scores is None:
        scores = [1] * len(boxes)
    for (box, score) in zip(boxes, scores):
        if score < drop_score:
            continue
        box = np.reshape(np.array(box), [-1, 1, 2]).astype(np.int64)
        image = cv2.polylines(np.array(image), [box], True, (255, 0, 0), 2)
    return image


def get_rotate_crop_image(img, points):
    '''
    img_height, img_width = img.shape[0:2]
    left = int(np.min(points[:, 0]))
    right = int(np.max(points[:, 0]))
    top = int(np.min(points[:, 1]))
    bottom = int(np.max(points[:, 1]))
    img_crop = img[top:bottom, left:right, :].copy()
    points[:, 0] = points[:, 0] - left
    points[:, 1] = points[:, 1] - top
    '''
    assert len(points) == 4, "shape of points must be 4*2"
    img_crop_width = int(
        max(
            np.linalg.norm(points[0] - points[1]),
            np.linalg.norm(points[2] - points[3])))
    img_crop_height = int(
        max(
            np.linalg.norm(points[0] - points[3]),
            np.linalg.norm(points[1] - points[2])))
    pts_std = np.float32([[0, 0], [img_crop_width, 0],
                          [img_crop_width, img_crop_height],
                          [0, img_crop_height]])
    M = cv2.getPerspectiveTransform(points, pts_std)
    dst_img = cv2.warpPerspective(
        img,
        M, (img_crop_width, img_crop_height),
        borderMode=cv2.BORDER_REPLICATE,
        flags=cv2.INTER_CUBIC)
    dst_img_height, dst_img_width = dst_img.shape[0:2]
    if dst_img_height * 1.0 / dst_img_width >= 1.5:
        dst_img = np.rot90(dst_img)
    return dst_img


def check_gpu(use_gpu):
    if use_gpu and not paddle.is_compiled_with_cuda():
        use_gpu = False
    return use_gpu


if __name__ == '__main__':
    pass