gm_try.py

import argparse
import glob
import json
import math
import operator
import os
import shutil
import sys

import numpy as np

#----------------------------------------------------#
#   用于计算mAP
#   代码克隆自https://github.com/Cartucho/mAP
#----------------------------------------------------#
MINOVERLAP = 0.5 # default value (defined in the PASCAL VOC2012 challenge)

parser = argparse.ArgumentParser()
parser.add_argument('-na', '--no-animation', help="no animation is shown.", action="store_true")
parser.add_argument('-np', '--no-plot', help="no plot is shown.", action="store_true")
parser.add_argument('-q', '--quiet', help="minimalistic console output.", action="store_true")
# argparse receiving list of classes to be ignored
parser.add_argument('-i', '--ignore', nargs='+', type=str, help="ignore a list of classes.")
# argparse receiving list of classes with specific IoU (e.g., python main.py --set-class-iou person 0.7)
parser.add_argument('--set-class-iou', nargs='+', type=str, help="set IoU for a specific class.")
args = parser.parse_args()
'''
    0,0 ------> x (width)
     |
     |  (Left,Top)
     |      *_________
     |      |         |
            |         |
     y      |_________|
  (height)            *
                (Right,Bottom)
'''
# if there are no classes to ignore then replace None by empty list
if args.ignore is None:
    args.ignore = []

specific_iou_flagged = False
if args.set_class_iou is not None:
    specific_iou_flagged = True

# make sure that the cwd() is the location of the python script (so that every path makes sense)
os.chdir(os.path.dirname(os.path.abspath(__file__)))

#GT_PATH = os.path.join(os.getcwd(), 'input', 'ground-truth')
GT_PATH = "/media/data3/jian/Text_Detection/YOLOV3/labels/valid"
DR_PATH = os.path.join(os.getcwd(), 'input', 'detection-results')
# if there are no images then no animation can be shown
IMG_PATH = os.path.join(os.getcwd(), 'input', 'images-optional')
#IMG_PATH = "/media/data3/jian/Text_Detection/YOLOV3/images/valid"
if os.path.exists(IMG_PATH): 
    for dirpath, dirnames, files in os.walk(IMG_PATH):
        if not files:
            # no image files found
            args.no_animation = True
else:
    args.no_animation = True

# try to import OpenCV if the user didn't choose the option --no-animation
show_animation = False
if not args.no_animation:
    try:
        import cv2
        show_animation = True
    except ImportError:
        print("\"opencv-python\" not found, please install to visualize the results.")
        args.no_animation = True

# try to import Matplotlib if the user didn't choose the option --no-plot
draw_plot = False
if not args.no_plot:
    try:
        import matplotlib.pyplot as plt
        draw_plot = True
        print("part1")
    except ImportError:
        print("\"matplotlib\" not found, please install it to get the resulting plots.")
        args.no_plot = True

def log_average_miss_rate(precision, fp_cumsum, num_images):
    """
        log-average miss rate:
            Calculated by averaging miss rates at 9 evenly spaced FPPI points
            between 10e-2 and 10e0, in log-space.

        output:
                lamr | log-average miss rate
                mr | miss rate
                fppi | false positives per image

        references:
            [1] Dollar, Piotr, et al. "Pedestrian Detection: An Evaluation of the
               State of the Art." Pattern Analysis and Machine Intelligence, IEEE
               Transactions on 34.4 (2012): 743 - 761.
    """

    # if there were no detections of that class
    if precision.size == 0:
        lamr = 0
        mr = 1
        fppi = 0
        return lamr, mr, fppi

    fppi = fp_cumsum / float(num_images)
    mr = (1 - precision)

    fppi_tmp = np.insert(fppi, 0, -1.0)
    mr_tmp = np.insert(mr, 0, 1.0)

    # Use 9 evenly spaced reference points in log-space
    ref = np.logspace(-2.0, 0.0, num = 9)
    for i, ref_i in enumerate(ref):
        # np.where() will always find at least 1 index, since min(ref) = 0.01 and min(fppi_tmp) = -1.0
        j = np.where(fppi_tmp <= ref_i)[-1][-1]
        ref[i] = mr_tmp[j]

    # log(0) is undefined, so we use the np.maximum(1e-10, ref)
    lamr = math.exp(np.mean(np.log(np.maximum(1e-10, ref))))

    return lamr, mr, fppi

"""
 throw error and exit
"""
def error(msg):
    print(msg)
    sys.exit(0)

"""
 check if the number is a float between 0.0 and 1.0
"""
def is_float_between_0_and_1(value):
    try:
        val = float(value)
        if val > 0.0 and val < 1.0:
            return True
        else:
            return False
    except ValueError:
        return False

"""
 Calculate the AP given the recall and precision array
    1st) We compute a version of the measured precision/recall curve with
         precision monotonically decreasing
    2nd) We compute the AP as the area under this curve by numerical integration.
"""
def voc_ap(rec, prec):
    """
    --- Official matlab code VOC2012---
    mrec=[0 ; rec ; 1];
    mpre=[0 ; prec ; 0];
    for i=numel(mpre)-1:-1:1
            mpre(i)=max(mpre(i),mpre(i+1));
    end
    i=find(mrec(2:end)~=mrec(1:end-1))+1;
    ap=sum((mrec(i)-mrec(i-1)).*mpre(i));
    """
    rec.insert(0, 0.0) # insert 0.0 at begining of list
    rec.append(1.0) # insert 1.0 at end of list
    mrec = rec[:]
    prec.insert(0, 0.0) # insert 0.0 at begining of list
    prec.append(0.0) # insert 0.0 at end of list
    mpre = prec[:]
    """
     This part makes the precision monotonically decreasing
        (goes from the end to the beginning)
        matlab: for i=numel(mpre)-1:-1:1
                    mpre(i)=max(mpre(i),mpre(i+1));
    """
    # matlab indexes start in 1 but python in 0, so I have to do:
    #     range(start=(len(mpre) - 2), end=0, step=-1)
    # also the python function range excludes the end, resulting in:
    #     range(start=(len(mpre) - 2), end=-1, step=-1)
    for i in range(len(mpre)-2, -1, -1):
        mpre[i] = max(mpre[i], mpre[i+1])
    """
     This part creates a list of indexes where the recall changes
        matlab: i=find(mrec(2:end)~=mrec(1:end-1))+1;
    """
    i_list = []
    for i in range(1, len(mrec)):
        if mrec[i] != mrec[i-1]:
            i_list.append(i) # if it was matlab would be i + 1
    """
     The Average Precision (AP) is the area under the curve
        (numerical integration)
        matlab: ap=sum((mrec(i)-mrec(i-1)).*mpre(i));
    """
    ap = 0.0
    for i in i_list:
        ap += ((mrec[i]-mrec[i-1])*mpre[i])
    
    print(ap, mrec, mpre)
    return ap, mrec, mpre

"""
 Convert the lines of a file to a list
"""
def file_lines_to_list(path):
    # open txt file lines to a list
    with open(path) as f:
        content = f.readlines()
    # remove whitespace characters like `\n` at the end of each line
    content = [x.strip() for x in content]
    return content

"""
 Draws text in image
"""
def draw_text_in_image(img, text, pos, color, line_width):
    font = cv2.FONT_HERSHEY_PLAIN
    fontScale = 1
    lineType = 1
    bottomLeftCornerOfText = pos
    cv2.putText(img, text,
            bottomLeftCornerOfText,
            font,
            fontScale,
            color,
            lineType)
    text_width, _ = cv2.getTextSize(text, font, fontScale, lineType)[0]
    return img, (line_width + text_width)

"""
 Plot - adjust axes
"""
def adjust_axes(r, t, fig, axes):
    # get text width for re-scaling
    bb = t.get_window_extent(renderer=r)
    text_width_inches = bb.width / fig.dpi
    # get axis width in inches
    current_fig_width = fig.get_figwidth()
    new_fig_width = current_fig_width + text_width_inches
    propotion = new_fig_width / current_fig_width
    # get axis limit
    x_lim = axes.get_xlim()
    axes.set_xlim([x_lim[0], x_lim[1]*propotion])

"""
 Draw plot using Matplotlib
"""
def draw_plot_func(dictionary, n_classes, window_title, plot_title, x_label, output_path, to_show, plot_color, true_p_bar):
    # sort the dictionary by decreasing value, into a list of tuples
    sorted_dic_by_value = sorted(dictionary.items(), key=operator.itemgetter(1))
    # unpacking the list of tuples into two lists
    sorted_keys, sorted_values = zip(*sorted_dic_by_value)
    # 
    if true_p_bar != "":
        """
         Special case to draw in:
            - green -> TP: True Positives (object detected and matches ground-truth)
            - red -> FP: False Positives (object detected but does not match ground-truth)
            - orange -> FN: False Negatives (object not detected but present in the ground-truth)
        """
        fp_sorted = []
        tp_sorted = []
        for key in sorted_keys:
            fp_sorted.append(dictionary[key] - true_p_bar[key])
            tp_sorted.append(true_p_bar[key])
        plt.barh(range(n_classes), fp_sorted, align='center', color='crimson', label='False Positive')
        plt.barh(range(n_classes), tp_sorted, align='center', color='forestgreen', label='True Positive', left=fp_sorted)
        # add legend
        plt.legend(loc='lower right')
        """
         Write number on side of bar
        """
        fig = plt.gcf() # gcf - get current figure
        axes = plt.gca()
        r = fig.canvas.get_renderer()
        for i, val in enumerate(sorted_values):
            fp_val = fp_sorted[i]
            tp_val = tp_sorted[i]
            fp_str_val = " " + str(fp_val)
            tp_str_val = fp_str_val + " " + str(tp_val)
            # trick to paint multicolor with offset:
            # first paint everything and then repaint the first number
            t = plt.text(val, i, tp_str_val, color='forestgreen', va='center', fontweight='bold')
            plt.text(val, i, fp_str_val, color='crimson', va='center', fontweight='bold')
            if i == (len(sorted_values)-1): # largest bar
                adjust_axes(r, t, fig, axes)
    else:
        plt.barh(range(n_classes), sorted_values, color=plot_color)
        """
         Write number on side of bar
        """
        fig = plt.gcf() # gcf - get current figure
        axes = plt.gca()
        r = fig.canvas.get_renderer()
        for i, val in enumerate(sorted_values):
            str_val = " " + str(val) # add a space before
            if val < 1.0:
                str_val = " {0:.2f}".format(val)
            t = plt.text(val, i, str_val, color=plot_color, va='center', fontweight='bold')
            # re-set axes to show number inside the figure
            if i == (len(sorted_values)-1): # largest bar
                adjust_axes(r, t, fig, axes)
    # set window title
    fig.canvas.set_window_title(window_title)
    # write classes in y axis
    tick_font_size = 12
    plt.yticks(range(n_classes), sorted_keys, fontsize=tick_font_size)
    """
     Re-scale height accordingly
    """
    init_height = fig.get_figheight()
    # comput the matrix height in points and inches
    dpi = fig.dpi
    height_pt = n_classes * (tick_font_size * 1.4) # 1.4 (some spacing)
    height_in = height_pt / dpi
    # compute the required figure height 
    top_margin = 0.15 # in percentage of the figure height
    bottom_margin = 0.05 # in percentage of the figure height
    figure_height = height_in / (1 - top_margin - bottom_margin)
    # set new height
    if figure_height > init_height:
        fig.set_figheight(figure_height)

    # set plot title
    plt.title(plot_title, fontsize=14)
    # set axis titles
    # plt.xlabel('classes')
    plt.xlabel(x_label, fontsize='large')
    # adjust size of window
    fig.tight_layout()
    # save the plot
    fig.savefig(output_path)
    # show image
    if to_show:
        plt.show()
    # close the plot
    plt.close()

"""
 Create a ".temp_files/" and "results/" directory
"""
print("create temp file")
TEMP_FILES_PATH = ".temp_files"
if not os.path.exists(TEMP_FILES_PATH): # if it doesn't exist already
    os.makedirs(TEMP_FILES_PATH)
results_files_path = "results"
if os.path.exists(results_files_path): # if it exist already
    # reset the results directory
    shutil.rmtree(results_files_path)

os.makedirs(results_files_path)
if draw_plot:
    os.makedirs(os.path.join(results_files_path, "AP"))
    os.makedirs(os.path.join(results_files_path, "F1"))
    os.makedirs(os.path.join(results_files_path, "Recall"))
    os.makedirs(os.path.join(results_files_path, "Precision"))
if show_animation:
    os.makedirs(os.path.join(results_files_path, "images", "detections_one_by_one"))
print("create temp and 4 sub files success")

"""
 ground-truth
     Load each of the ground-truth files into a temporary ".json" file.
     Create a list of all the class names present in the ground-truth (gt_classes).
"""
# get a list with the ground-truth files
ground_truth_files_list = glob.glob(GT_PATH + '/*.txt')
if len(ground_truth_files_list) == 0:
    error("Error: No ground-truth files found!")
ground_truth_files_list.sort()
# dictionary with counter per class
gt_counter_per_class = {}
counter_images_per_class = {}

print("decompose ground truth file")
i=0
for txt_file in ground_truth_files_list:
    if i<=3:
        print(txt_file)
        file_id = txt_file.split(".txt", 1)[0]
        file_id = os.path.basename(os.path.normpath(file_id))
        # check if there is a correspondent detection-results file
        temp_path = os.path.join(DR_PATH, (file_id + ".txt"))
        if not os.path.exists(temp_path):
            error_msg = "Error. File not found: {}\n".format(temp_path)
            error_msg += "(You can avoid this error message by running extra/intersect-gt-and-dr.py)"
            error(error_msg)
        lines_list = file_lines_to_list(txt_file)
        #print(lines_list)
        bounding_boxes = []
        is_difficult = False
        already_seen_classes = []
        for line in lines_list:
            try:
                if "difficult" in line:
                    class_name, left, top, right, bottom, _difficult = line.split(" ")
                    is_difficult = True
                else:
                    class_name, left, top, right, bottom, width, height = line.split(" ")
            except:
                if "difficult" in line:
                    line_split = line.split()
                    _difficult = line_split[-1]
                    bottom = line_split[-2]
                    right = line_split[-3]
                    top = line_split[-4]
                    left = line_split[-5]
                    class_name = ""
                    for name in line_split[:-5]:
                        class_name += name
                    is_difficult = True
                else:
                    line_split = line.split()
                    bottom = line_split[-1]
                    right = line_split[-2]
                    top = line_split[-3]
                    left = line_split[-4]
                    class_name = ""
                    for name in line_split[:-4]:
                        class_name += name
            # check if class is in the ignore list, if yes skip
            if class_name in args.ignore:
                continue
            bbox = left + " " + top + " " + right + " " +bottom
            if is_difficult:
                bounding_boxes.append({"class_name":class_name, "bbox":bbox, "used":False, "difficult":True})
                is_difficult = False
            else:
                bounding_boxes.append({"class_name":class_name, "bbox":bbox, "used":False})
                # count that object
                if class_name in gt_counter_per_class:
                    gt_counter_per_class[class_name] += 1
                else:
                    # if class didn't exist yet
                    gt_counter_per_class[class_name] = 1

                if class_name not in already_seen_classes:
                    if class_name in counter_images_per_class:
                        counter_images_per_class[class_name] += 1
                    else:
                        # if class didn't exist yet
                        counter_images_per_class[class_name] = 1
                    already_seen_classes.append(class_name)        
        # dump bounding_boxes into a ".json" file
        with open(TEMP_FILES_PATH + "/" + file_id + "_ground_truth.json", 'w') as outfile:
            json.dump(bounding_boxes, outfile)
        i+=1
print("decompose success")
print("part3")
gt_classes = list(gt_counter_per_class.keys())
# let's sort the classes alphabetically
gt_classes = sorted(gt_classes)
n_classes = len(gt_classes)
print(gt_classes)