test.py

"""  
Copyright (c) 2019-present NAVER Corp.
MIT License
"""

# -*- coding: utf-8 -*-
import time
from collections import OrderedDict

import cv2
import numpy as np
import torch
from torch.autograd import Variable

import craft_utils
import imgproc


def copyStateDict(state_dict):
    if list(state_dict.keys())[0].startswith("module"):
        start_idx = 1
    else:
        start_idx = 0
    new_state_dict = OrderedDict()
    for k, v in state_dict.items():
        name = ".".join(k.split(".")[start_idx:])
        new_state_dict[name] = v
    return new_state_dict


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


def test_net(net, image, text_threshold, link_threshold, low_text, cuda, poly, args, refine_net=None):
    t0 = time.time()

    # resize
    img_resized, target_ratio, size_heatmap = imgproc.resize_aspect_ratio(image, args['canvas_size'],
                                                                          interpolation=cv2.INTER_LINEAR,
                                                                          mag_ratio=args['mag_ratio'])
    ratio_h = ratio_w = 1 / target_ratio

    # preprocessing
    x = imgproc.normalizeMeanVariance(img_resized)
    x = torch.from_numpy(x).permute(2, 0, 1)  # [h, w, c] to [c, h, w]
    x = Variable(x.unsqueeze(0))  # [c, h, w] to [b, c, h, w]
    if cuda:
        x = x.cuda()

    # forward pass
    with torch.no_grad():
        y, feature = net(x)

    # make score and link map
    score_text = y[0, :, :, 0].cpu().data.numpy()
    score_link = y[0, :, :, 1].cpu().data.numpy()

    # refine link
    if refine_net is not None:
        with torch.no_grad():
            y_refiner = refine_net(y, feature)
        score_link = y_refiner[0, :, :, 0].cpu().data.numpy()

    t0 = time.time() - t0
    t1 = time.time()

    # Post-processing
    boxes, polys, det_scores = craft_utils.getDetBoxes(score_text, score_link, text_threshold, link_threshold, low_text, poly)

    # coordinate adjustment
    boxes = craft_utils.adjustResultCoordinates(boxes, ratio_w, ratio_h)
    polys = craft_utils.adjustResultCoordinates(polys, ratio_w, ratio_h)
    for k in range(len(polys)):
        if polys[k] is None: polys[k] = boxes[k]

    t1 = time.time() - t1

    # render results (optional)
    render_img = score_text.copy()
    render_img = np.hstack((render_img, score_link))
    ret_score_text = imgproc.cvt2HeatmapImg(render_img)

    print("\ninfer/postproc time : {:.3f}/{:.3f}".format(t0, t1))

    return boxes, polys, ret_score_text, det_scores