Moving files from MTGCardDetector
| New file |
| | |
| | | import cv2 |
| | | import numpy as np |
| | | import pandas as pd |
| | | import math |
| | | from screeninfo import get_monitors |
| | | |
| | | |
| | | def detect_a_card(img, thresh_val=80, blur_radius=None, dilate_radius=None, min_hyst=80, max_hyst=200, |
| | | min_line_length=None, max_line_gap=None, debug=False): |
| | | dim_img = (len(img[0]), len(img)) # (width, height) |
| | | # Intermediate variables |
| | | |
| | | # Default values |
| | | if blur_radius is None: |
| | | blur_radius = math.floor(min(dim_img) / 100 + 0.5) // 2 * 2 + 1 # Rounded to the nearest odd |
| | | if dilate_radius is None: |
| | | dilate_radius = math.floor(min(dim_img) / 67 + 0.5) |
| | | if min_line_length is None: |
| | | min_line_length = min(dim_img) / 10 |
| | | if max_line_gap is None: |
| | | max_line_gap = min(dim_img) / 10 |
| | | |
| | | thresh_radius = math.floor(min(dim_img) / 20 + 0.5) // 2 * 2 + 1 # Rounded to the nearest odd |
| | | |
| | | img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) |
| | | # Median blur better removes background textures than Gaussian blur |
| | | img_blur = cv2.medianBlur(img_gray, blur_radius) |
| | | # Truncate the bright area while detecting the border |
| | | img_thresh = cv2.adaptiveThreshold(img_blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, |
| | | cv2.THRESH_BINARY_INV, thresh_radius, 20) |
| | | #_, img_thresh = cv2.threshold(img_blur, thresh_val, 255, cv2.THRESH_TRUNC) |
| | | |
| | | # Dilate the image to emphasize thick borders around the card |
| | | kernel_dilate = np.ones((dilate_radius, dilate_radius), np.uint8) |
| | | #img_dilate = cv2.dilate(img_thresh, kernel_dilate, iterations=1) |
| | | img_dilate = cv2.erode(img_thresh, kernel_dilate, iterations=1) |
| | | |
| | | img_contour = img_dilate.copy() |
| | | _, contours, _ = cv2.findContours(img_contour, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) |
| | | img_contour = cv2.cvtColor(img_contour, cv2.COLOR_GRAY2BGR) |
| | | img_contour = cv2.drawContours(img_contour, contours, -1, (128, 128, 128), 1) |
| | | card_found = contours is not None |
| | | print(len(contours)) |
| | | print([len(contour) for contour in contours]) |
| | | |
| | | # find the biggest area |
| | | c = max(contours, key=cv2.contourArea) |
| | | |
| | | x, y, w, h = cv2.boundingRect(c) |
| | | # draw the book contour (in green) |
| | | img_contour = cv2.drawContours(img_contour, [c], -1, (0, 255, 0), 1) |
| | | |
| | | # Canny edge - low minimum hysteresis to detect glowed area, |
| | | # and high maximum hysteresis to compensate for high false positives. |
| | | img_canny = cv2.Canny(img_dilate, min_hyst, max_hyst) |
| | | #img_canny = img_dilate |
| | | # Apply Hough transformation to detect the edges |
| | | detected_lines = cv2.HoughLinesP(img_dilate, 1, np.pi / 180, threshold=60, |
| | | minLineLength=min_line_length, |
| | | maxLineGap=max_line_gap) |
| | | card_found = detected_lines is not None |
| | | print(len(detected_lines)) |
| | | |
| | | if card_found: |
| | | if debug: |
| | | img_hough = cv2.cvtColor(img_dilate.copy(), cv2.COLOR_GRAY2BGR) |
| | | for line in detected_lines: |
| | | x1, y1, x2, y2 = line[0] |
| | | cv2.line(img_hough, (x1, y1), (x2, y2), (0, 0, 255), 1) |
| | | elif not debug: |
| | | print('Hough couldn\'t find any lines') |
| | | |
| | | # Debug: display intermediate results from various steps |
| | | if debug: |
| | | img_blank = np.zeros((len(img), len(img[0]), 3), np.uint8) |
| | | img_thresh = cv2.cvtColor(img_thresh, cv2.COLOR_GRAY2BGR) |
| | | img_dilate = cv2.cvtColor(img_dilate, cv2.COLOR_GRAY2BGR) |
| | | #img_canny = cv2.cvtColor(img_canny, cv2.COLOR_GRAY2BGR) |
| | | if not card_found: |
| | | img_hough = img_blank |
| | | |
| | | # Append all images together |
| | | img_row_1 = np.concatenate((img, img_thresh), axis=1) |
| | | img_row_2 = np.concatenate((img_contour, img_hough), axis=1) |
| | | img_result = np.concatenate((img_row_1, img_row_2), axis=0) |
| | | |
| | | # Resize the final image to fit into the main monitor's resolution |
| | | screen_size = get_monitors()[0] |
| | | resize_ratio = max(len(img_result[0]) / screen_size.width, len(img_result) / screen_size.height, 1) |
| | | img_result = cv2.resize(img_result, (int(len(img_result[0]) // resize_ratio), |
| | | int(len(img_result) // resize_ratio))) |
| | | cv2.imshow('Result', img_result) |
| | | cv2.waitKey(0) |
| | | |
| | | # TODO: output meaningful data |
| | | return card_found |
| | | |
| | | def main(): |
| | | img_test = cv2.imread('data/li38_handOfCards.jpg') |
| | | card_found = detect_a_card(img_test, |
| | | #dilate_radius=5, |
| | | #thresh_val=100, |
| | | #min_hyst=40, |
| | | #max_hyst=160, |
| | | #min_line_length=50, |
| | | #max_line_gap=100, |
| | | debug=True) |
| | | if card_found: |
| | | return |
| | | return |
| | | for dilate_radius in range(1, 6): |
| | | for min_hyst in range(50, 91, 10): |
| | | for max_hyst in range(180, 119, -20): |
| | | print('dilate_radius=%d, min_hyst=%d, max_hyst=%d: ' % (dilate_radius, min_hyst, max_hyst), |
| | | end='', flush=True) |
| | | card_found = detect_a_card(img_test, dilate_radius=dilate_radius, |
| | | min_hyst=min_hyst, max_hyst=max_hyst, debug=True) |
| | | if card_found: |
| | | print('Card found') |
| | | else: |
| | | print('Not found') |
| | | |
| | | if __name__ == '__main__': |
| | | main() |
| New file |
| | |
| | | from urllib import request |
| | | import ast |
| | | import json |
| | | import pandas as pd |
| | | import re |
| | | import os |
| | | import transform_data |
| | | import time |
| | | |
| | | all_set_list = ['cmd', 'bfz', 'all', 'ulg', |
| | | 'mrd', 'dst', '5dn', 'chk', 'bok', 'sok', 'rav', 'gpt', 'dis', 'csp', 'tsp', 'plc', 'fut', |
| | | '10e', 'lrw', 'mor', 'shm', 'eve', 'ala', 'con', 'arb', 'm10', 'zen', 'wwk', 'roe', 'm11', 'som', 'mbs', |
| | | 'nph', 'm12', 'isd', 'dka', 'avr', 'm13', 'rtr', 'gtc', 'dgm', 'm14', 'ths', 'bng', 'jou'] |
| | | |
| | | |
| | | def fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+format:modern+lang:en+frame:2003', |
| | | csv_name=''): |
| | | has_more = True |
| | | cards = [] |
| | | # get cards dataset as a json from the query |
| | | while has_more: |
| | | res_file_dir, http_message = request.urlretrieve(url) |
| | | with open(res_file_dir, 'r') as res_file: |
| | | res_json = json.loads(res_file.read()) |
| | | cards += res_json['data'] |
| | | has_more = res_json['has_more'] |
| | | if has_more: |
| | | url = res_json['next_page'] |
| | | print(len(cards)) |
| | | |
| | | # Convert them into a dataframe, and truncate unnecessary columns |
| | | df = pd.DataFrame.from_dict(cards) |
| | | |
| | | if csv_name != '': |
| | | df = df[['artist', 'border_color', 'collector_number', 'color_identity', 'colors', 'flavor_text', 'image_uris', |
| | | 'mana_cost', 'legalities', 'name', 'oracle_text', 'rarity', 'type_line', 'set', 'set_name', 'power', |
| | | 'toughness']] |
| | | #df.to_json(csv_name) |
| | | df.to_csv(csv_name, sep=';') # Comma doesn't work, since some columns are saved as a dict |
| | | |
| | | return df |
| | | |
| | | |
| | | def load_all_cards_text(csv_name): |
| | | #with open(csv_name, 'r') as json_file: |
| | | # cards = json.loads(json_file.read()) |
| | | #df = pd.DataFrame.from_dict(cards) |
| | | df = pd.read_csv(csv_name, sep=';') |
| | | return df |
| | | |
| | | |
| | | # Pulled from Django framework (https://github.com/django/django/blob/master/django/utils/text.py) |
| | | def get_valid_filename(s): |
| | | """ |
| | | Return the given string converted to a string that can be used for a clean |
| | | filename. Remove leading and trailing spaces; convert other spaces to |
| | | underscores; and remove anything that is not an alphanumeric, dash, |
| | | underscore, or dot. |
| | | >>> get_valid_filename("john's portrait in 2004.jpg") |
| | | 'johns_portrait_in_2004.jpg' |
| | | """ |
| | | s = str(s).strip().replace(' ', '_') |
| | | return re.sub(r'(?u)[^-\w.]', '', s) |
| | | |
| | | |
| | | def fetch_all_cards_image(df, out_dir='', size='png'): |
| | | if isinstance(df, pd.Series): |
| | | fetch_card_image(df, out_dir, size) |
| | | else: |
| | | for ind, row in df.iterrows(): |
| | | fetch_card_image(row, out_dir, size) |
| | | |
| | | |
| | | def fetch_card_image(row, out_dir='', size='png'): |
| | | if isinstance(row['image_uris'], str): # For some reason, dict isn't being parsed in the previous step |
| | | png_url = ast.literal_eval(row['image_uris'])[size] |
| | | else: |
| | | png_url = row['image_uris'][size] |
| | | if out_dir == '': |
| | | out_dir = 'data/%s/%s' % (size, row['set']) |
| | | if not os.path.exists(out_dir): |
| | | os.makedirs(out_dir) |
| | | img_name = '%s/%s_%s.png' % (out_dir, row['collector_number'], get_valid_filename(row['name'])) |
| | | if not os.path.isfile(img_name): |
| | | request.urlretrieve(png_url, filename=img_name) |
| | | print(img_name) |
| | | |
| | | |
| | | def main(): |
| | | for set_name in all_set_list: |
| | | csv_name = '%s/csv/%s.csv' % (transform_data.data_dir, set_name) |
| | | print(csv_name) |
| | | if not os.path.isfile(csv_name): |
| | | df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=set:%s+lang:en' |
| | | % set_name, csv_name=csv_name) |
| | | else: |
| | | df = load_all_cards_text(csv_name) |
| | | time.sleep(1) |
| | | #fetch_all_cards_image(df, out_dir='../usb/data/png/%s' % set_name) |
| | | #df = fetch_all_cards_text(url='https://api.scryfall.com/cards/search?q=layout:normal+lang:en+frame:2003', |
| | | # csv_name='data/csv/all.csv') |
| | | pass |
| | | |
| | | |
| | | if __name__ == '__main__': |
| | | main() |
| | | pass |
| New file |
| | |
| | | from glob import glob |
| | | import matplotlib.pyplot as plt |
| | | import matplotlib.image as mpimage |
| | | import pickle |
| | | import math |
| | | import random |
| | | import os |
| | | import re |
| | | import cv2 |
| | | import fetch_data |
| | | import sys |
| | | import numpy as np |
| | | import pandas as pd |
| | | import transform_data |
| | | |
| | | # Referenced from geaxgx's playing-card-detection: https://github.com/geaxgx/playing-card-detection |
| | | class Backgrounds: |
| | | def __init__(self, images=None, dumps_dir='data/dtd/images'): |
| | | if images is not None: |
| | | self._images = images |
| | | else: # load from pickle |
| | | if not os.path.exists(dumps_dir): |
| | | print('Warning: directory for dump %s doesn\'t exist' % dumps_dir) |
| | | return |
| | | self._images = [] |
| | | for dump_name in glob(dumps_dir + '/*.pck'): |
| | | with open(dump_name, 'rb') as dump: |
| | | print('Loading ' + dump_name) |
| | | images = pickle.load(dump) |
| | | self._images += images |
| | | if len(self._images) == 0: |
| | | self._images = load_dtd() |
| | | print('# of images loaded: %d' % len(self._images)) |
| | | |
| | | def get_random(self, display=False): |
| | | bg = self._images[random.randint(0, len(self._images) - 1)] |
| | | if display: |
| | | plt.show(bg) |
| | | return bg |
| | | |
| | | |
| | | def load_dtd(dtd_dir='data/dtd/images', dump_it=True, dump_batch_size=1000): |
| | | if not os.path.exists(dtd_dir): |
| | | print('Warning: directory for DTD 5s doesn\'t exist.' % dtd_dir) |
| | | print('You can download the dataset using this command:' |
| | | '!wget https://www.robots.ox.ac.uk/~vgg/data/dtd/download/dtd-r1.0.1.tar.gz') |
| | | return [] |
| | | bg_images = [] |
| | | # Search the directory for all images, and append them |
| | | for subdir in glob(dtd_dir + "/*"): |
| | | for f in glob(subdir + "/*.jpg"): |
| | | bg_images.append(mpimage.imread(f)) |
| | | print("# of images loaded :", len(bg_images)) |
| | | |
| | | # Save them as a pickle if necessary |
| | | if dump_it: |
| | | for i in range(math.ceil(len(bg_images) / dump_batch_size)): |
| | | dump_name = '%s/dtd_dump_%d.pck' % (dtd_dir, i) |
| | | with open(dump_name, 'wb') as dump: |
| | | print('Dumping ' + dump_name) |
| | | pickle.dump(bg_images[i * dump_batch_size:(i + 1) * dump_batch_size], dump) |
| | | |
| | | return bg_images |
| | | |
| | | |
| | | def apply_bounding_box(img, card_info, display=False): |
| | | # List of detected objects to be fed into the neural net |
| | | # The first object is the entire card |
| | | detected_object_list = [transform_data.ExtractedObject('card', [(0, 0), (len(img[0]), 0), (len(img[0]), len(img)), (0, len(img))])] |
| | | ''' |
| | | # Mana symbol - They are located on the top right side of the card, next to the name |
| | | # Their position is stationary, and is right-aligned. |
| | | has_mana_cost = isinstance(card_info['mana_cost'], str) # Cards with no mana cost will have nan |
| | | if has_mana_cost: |
| | | mana_cost = re.findall('\{(.*?)\}', card_info['mana_cost']) |
| | | x_anchor = 683 |
| | | y_anchor = 65 |
| | | |
| | | # Cards with specific type or from old sets have their symbol at a different position |
| | | if card_info['set'] in ['8ed', 'mrd', 'dst', '5dn']: |
| | | y_anchor -= 2 |
| | | |
| | | for i in reversed(range(len(mana_cost))): |
| | | # Hybrid mana symbol are larger than a normal symbol |
| | | is_hybrid = '/' in mana_cost[i] |
| | | if is_hybrid: |
| | | x1 = x_anchor - 47 |
| | | x2 = x_anchor + 2 |
| | | y1 = y_anchor - 8 |
| | | y2 = y_anchor + 43 |
| | | x_anchor -= 45 |
| | | else: |
| | | x1 = x_anchor - 39 |
| | | x2 = x_anchor |
| | | y1 = y_anchor |
| | | y2 = y_anchor + 43 |
| | | x_anchor -= 37 |
| | | # Append them to the list of bounding box with the appropriate label |
| | | symbol_name = 'mana_symbol:' + mana_cost[i] |
| | | key_pts = [(x1, y1), (x2, y1), (x2, y2), (x1, y2)] |
| | | detected_object_list.append(transform_data.ExtractedObject(symbol_name, key_pts)) |
| | | |
| | | if display: |
| | | img_symbol = img[y1:y2, x1:x2] |
| | | cv2.imshow('symbol', img_symbol) |
| | | cv2.waitKey(0) |
| | | |
| | | # Set symbol - located on the right side of the type box in the centre of the card, next to the card type |
| | | # Only one symbol exists, and its colour varies by rarity. |
| | | if card_info['set'] in ['8ed']: |
| | | x1 = 622 |
| | | x2 = 670 |
| | | elif card_info['set'] in ['mrd', 'm10', 'm11', 'm12', 'm13', 'm14']: |
| | | x1 = 602 |
| | | x2 = 684 |
| | | elif card_info['set'] in ['dst']: |
| | | x1 = 636 |
| | | x2 = 673 |
| | | elif card_info['set'] in ['5dn']: |
| | | x1 = 630 |
| | | x2 = 675 |
| | | elif card_info['set'] in ['bok', 'rtr']: |
| | | x1 = 633 |
| | | x2 = 683 |
| | | elif card_info['set'] in ['sok', 'mbs']: |
| | | x1 = 638 |
| | | x2 = 683 |
| | | elif card_info['set'] in ['rav']: |
| | | x1 = 640 |
| | | x2 = 678 |
| | | elif card_info['set'] in ['csp']: |
| | | x1 = 650 |
| | | x2 = 683 |
| | | elif card_info['set'] in ['tsp', 'lrw', 'zen', 'wwk', 'ths']: |
| | | x1 = 640 |
| | | x2 = 683 |
| | | elif card_info['set'] in ['plc', 'fut', 'shm', 'eve']: |
| | | x1 = 625 |
| | | x2 = 685 |
| | | elif card_info['set'] in ['10e']: |
| | | x1 = 623 |
| | | x2 = 680 |
| | | elif card_info['set'] in ['mor', 'roe', 'bng']: |
| | | x1 = 637 |
| | | x2 = 687 |
| | | elif card_info['set'] in ['ala', 'arb']: |
| | | x1 = 635 |
| | | x2 = 680 |
| | | elif card_info['set'] in ['nph']: |
| | | x1 = 642 |
| | | x2 = 678 |
| | | elif card_info['set'] in ['gtc']: |
| | | x1 = 610 |
| | | x2 = 683 |
| | | elif card_info['set'] in ['dgm']: |
| | | x1 = 618 |
| | | x2 = 678 |
| | | else: |
| | | x1 = 630 |
| | | x2 = 683 |
| | | y1 = 589 |
| | | y2 = 636 |
| | | # Append them to the list of bounding box with the appropriate label |
| | | symbol_name = 'set_symbol:' + card_info['set'] |
| | | key_pts = [(x1, y1), (x2, y1), (x2, y2), (x1, y2)] |
| | | detected_object_list.append(transform_data.ExtractedObject(symbol_name, key_pts)) |
| | | |
| | | if display: |
| | | img_symbol = img[y1:y2, x1:x2] |
| | | cv2.imshow('symbol', img_symbol) |
| | | cv2.waitKey(0) |
| | | |
| | | # Name box - The long bar on the top with card name and mana symbols |
| | | # TODO |
| | | |
| | | # Type box - The long bar on the middle with card type and set symbols |
| | | # TODO |
| | | |
| | | # Image box - the large image on the top half of the card |
| | | # TODO |
| | | ''' |
| | | return detected_object_list |
| | | |
| | | |
| | | def main(): |
| | | random.seed() |
| | | #bg_images = load_dtd() |
| | | #bg = Backgrounds() |
| | | #bg.get_random(display=True) |
| | | |
| | | card_pool = pd.DataFrame() |
| | | for set_name in fetch_data.all_set_list: |
| | | df = fetch_data.load_all_cards_text('data/csv/%s.csv' % set_name) |
| | | #for _ in range(3): |
| | | # card_info = df.iloc[random.randint(0, df.shape[0] - 1)] |
| | | # # Currently ignoring planeswalker cards due to their different card layout |
| | | # is_planeswalker = 'Planeswalker' in card_info['type_line'] |
| | | # if not is_planeswalker: |
| | | # card_pool = card_pool.append(card_info) |
| | | card_pool = card_pool.append(df) |
| | | ''' |
| | | print(card_pool) |
| | | mana_symbol_set = set() |
| | | for _, card_info in card_pool.iterrows(): |
| | | has_mana_cost = isinstance(card_info['mana_cost'], str) |
| | | if has_mana_cost: |
| | | mana_cost = re.findall('\{(.*?)\}', card_info['mana_cost']) |
| | | for symbol in mana_cost: |
| | | mana_symbol_set.add(symbol) |
| | | |
| | | print(mana_symbol_set) |
| | | ''' |
| | | |
| | | for _, card_info in card_pool.iterrows(): |
| | | img_name = '../usb/data/png/%s/%s_%s.png' % (card_info['set'], card_info['collector_number'], |
| | | fetch_data.get_valid_filename(card_info['name'])) |
| | | print(img_name) |
| | | card_img = cv2.imread(img_name) |
| | | if card_img is None: |
| | | fetch_data.fetch_card_image(card_info, out_dir='../usb/data/png/%s' % card_info['set']) |
| | | card_img = cv2.imread(img_name) |
| | | detected_object_list = apply_bounding_box(card_img, card_info, display=True) |
| | | print(detected_object_list) |
| | | |
| | | return |
| | | |
| | | |
| | | if __name__ == '__main__': |
| | | main() |
| New file |
| | |
| | | import os |
| | | from glob import glob |
| | | import random |
| | | import transform_data |
| | | |
| | | |
| | | def main(): |
| | | random.seed() |
| | | data_list = [] |
| | | for subdir in glob('%s/train/*_10' % transform_data.data_dir): |
| | | for data in glob(subdir + "/*.jpg"): |
| | | data_list.append(os.path.abspath(data)) |
| | | random.shuffle(data_list) |
| | | |
| | | test_ratio = 0.1 |
| | | test_list = data_list[:int(test_ratio * len(data_list))] |
| | | train_list = data_list[int(test_ratio * len(data_list)):] |
| | | with open('%s/train_10.txt' % transform_data.darknet_dir, 'w') as train_txt: |
| | | for data in train_list: |
| | | train_txt.write(data + '\n') |
| | | with open('%s/test_10.txt' % transform_data.darknet_dir, 'w') as test_txt: |
| | | for data in test_list: |
| | | test_txt.write(data + '\n') |
| | | return |
| | | |
| | | |
| | | if __name__ == '__main__': |
| | | main() |
| New file |
| | |
| | | import os |
| | | import random |
| | | import math |
| | | import cv2 |
| | | import numpy as np |
| | | import imutils |
| | | import pandas as pd |
| | | import fetch_data |
| | | import generate_data |
| | | from shapely import geometry |
| | | import pytesseract |
| | | import imgaug as ia |
| | | from imgaug import augmenters as iaa |
| | | from imgaug import parameters as iap |
| | | |
| | | card_mask = cv2.imread('data/mask.png') |
| | | data_dir = os.path.abspath('/media/win10/data') |
| | | darknet_dir = os.path.abspath('darknet') |
| | | |
| | | |
| | | def key_pts_to_yolo(key_pts, w_img, h_img): |
| | | """ |
| | | Convert a list of keypoints into a yolo training format |
| | | :param key_pts: list of keypoints |
| | | :param w_img: width of the entire image |
| | | :param h_img: height of the entire image |
| | | :return: <x> <y> <width> <height> |
| | | """ |
| | | x1 = max(0, min([pt[0] for pt in key_pts])) |
| | | x2 = min(w_img, max([pt[0] for pt in key_pts])) |
| | | y1 = max(0, min([pt[1] for pt in key_pts])) |
| | | y2 = min(h_img, max([pt[1] for pt in key_pts])) |
| | | x = (x2 + x1) / 2 / w_img |
| | | y = (y2 + y1) / 2 / h_img |
| | | width = (x2 - x1) / w_img |
| | | height = (y2 - y1) / h_img |
| | | return x, y, width, height |
| | | |
| | | |
| | | class ImageGenerator: |
| | | """ |
| | | A template for generating a training image. |
| | | """ |
| | | def __init__(self, img_bg, class_ids, width, height, skew=None, cards=None): |
| | | """ |
| | | :param img_bg: background (textile) image |
| | | :param width: width of the training image |
| | | :param height: height of the training image |
| | | :param skew: 4 coordinates that indicates the corners (in normalized form) for perspective transform |
| | | :param cards: list of Card objects |
| | | """ |
| | | self.img_bg = img_bg |
| | | self.class_ids = class_ids |
| | | self.img_result = None |
| | | self.width = width |
| | | self.height = height |
| | | if cards is None: |
| | | self.cards = [] |
| | | else: |
| | | self.cards = cards |
| | | |
| | | # Compute transform matrix for perspective transform |
| | | if skew is not None: |
| | | orig_corner = np.array([[0, 0], [0, height], [width, height], [width, 0]], dtype=np.float32) |
| | | new_corner = np.array([[width * s[0], height * s[1]] for s in skew], dtype=np.float32) |
| | | self.M = cv2.getPerspectiveTransform(orig_corner, new_corner) |
| | | pass |
| | | else: |
| | | self.M = None |
| | | pass |
| | | |
| | | def add_card(self, card, x=None, y=None, theta=0.0, scale=1.0): |
| | | """ |
| | | Add a card to this generator scenario. |
| | | :param card: card to be added |
| | | :param x: new X-coordinate for the centre of the card |
| | | :param y: new Y-coordinate for the centre of the card |
| | | :param theta: new angle for the card |
| | | :param scale: new scale for the card |
| | | :return: none |
| | | """ |
| | | if x is None: |
| | | x = -len(card.img[0]) / 2 |
| | | if y is None: |
| | | y = -len(card.img) / 2 |
| | | self.cards.append(card) |
| | | card.x = x |
| | | card.y = y |
| | | card.theta = theta |
| | | card.scale = scale |
| | | pass |
| | | |
| | | def render(self, visibility=0.5, display=False, debug=False, aug=None): |
| | | """ |
| | | Display the current state of the generator |
| | | :return: none |
| | | """ |
| | | self.check_visibility(visibility=visibility) |
| | | #img_result = cv2.resize(self.img_bg, (self.width, self.height)) |
| | | img_result = np.zeros((self.height, self.width, 3), dtype=np.uint8) |
| | | |
| | | for card in self.cards: |
| | | if card.x == 0.0 and card.y == 0.0 and card.theta == 0.0 and card.scale == 1.0: |
| | | continue |
| | | card_x = int(card.x + 0.5) |
| | | card_y = int(card.y + 0.5) |
| | | #print(card_x, card_y, card.theta, card.scale) |
| | | |
| | | # Scale & rotate card image |
| | | img_card = cv2.resize(card.img, (int(len(card.img[0]) * card.scale), int(len(card.img) * card.scale))) |
| | | if aug is not None: |
| | | seq = iaa.Sequential([ |
| | | iaa.SimplexNoiseAlpha(first=iaa.Add(random.randrange(128)), size_px_max=[1, 3], |
| | | upscale_method="cubic"), # Lighting |
| | | ]) |
| | | img_card = seq.augment_image(img_card) |
| | | mask_scale = cv2.resize(card_mask, (int(len(card_mask[0]) * card.scale), int(len(card_mask) * card.scale))) |
| | | img_mask = cv2.bitwise_and(img_card, mask_scale) |
| | | img_rotate = imutils.rotate_bound(img_mask, card.theta / math.pi * 180) |
| | | |
| | | # Calculate the position of the card image in relation to the background |
| | | # Crop the card image if it's out of boundary |
| | | card_w = len(img_rotate[0]) |
| | | card_h = len(img_rotate) |
| | | card_crop_x1 = max(0, card_w // 2 - card_x) |
| | | card_crop_x2 = min(card_w, card_w // 2 + len(img_result[0]) - card_x) |
| | | card_crop_y1 = max(0, card_h // 2 - card_y) |
| | | card_crop_y2 = min(card_h, card_h // 2 + len(img_result) - card_y) |
| | | img_card_crop = img_rotate[card_crop_y1:card_crop_y2, card_crop_x1:card_crop_x2] |
| | | |
| | | # Calculate the position of the corresponding area in the background |
| | | bg_crop_x1 = max(0, card_x - (card_w // 2)) |
| | | bg_crop_x2 = min(len(img_result[0]), int(card_x + (card_w / 2) + 0.5)) |
| | | bg_crop_y1 = max(0, card_y - (card_h // 2)) |
| | | bg_crop_y2 = min(len(img_result), int(card_y + (card_h / 2) + 0.5)) |
| | | img_result_crop = img_result[bg_crop_y1:bg_crop_y2, bg_crop_x1:bg_crop_x2] |
| | | |
| | | # Override the background with the current card |
| | | img_result_crop = np.where(img_card_crop, img_card_crop, img_result_crop) |
| | | img_result[bg_crop_y1:bg_crop_y2, bg_crop_x1:bg_crop_x2] = img_result_crop |
| | | |
| | | if debug: |
| | | for ext_obj in card.objects: |
| | | if ext_obj.visible: |
| | | for pt in ext_obj.key_pts: |
| | | cv2.circle(img_result, card.coordinate_in_generator(pt[0], pt[1]), 2, (1, 1, 255), 10) |
| | | bounding_box = card.bb_in_generator(ext_obj.key_pts) |
| | | cv2.rectangle(img_result, bounding_box[0], bounding_box[2], (1, 255, 1), 5) |
| | | |
| | | ''' |
| | | try: |
| | | text = pytesseract.image_to_string(img_result, output_type=pytesseract.Output.DICT) |
| | | print(text) |
| | | except pytesseract.pytesseract.TesseractError: |
| | | pass |
| | | ''' |
| | | img_result = cv2.GaussianBlur(img_result, (5, 5), 0) |
| | | |
| | | if self.M is not None: |
| | | img_result = cv2.warpPerspective(img_result, self.M, (self.width, self.height)) |
| | | if debug: |
| | | for card in self.cards: |
| | | for ext_obj in card.objects: |
| | | if ext_obj.visible: |
| | | new_pts = np.array([[list(card.coordinate_in_generator(pt[0], pt[1]))] |
| | | for pt in ext_obj.key_pts], dtype=np.float32) |
| | | new_pts = cv2.perspectiveTransform(new_pts, self.M) |
| | | for pt in new_pts: |
| | | cv2.circle(img_result, (pt[0][0], pt[0][1]), 2, (255, 1, 1), 10) |
| | | |
| | | img_bg = cv2.resize(self.img_bg, (self.width, self.height)) |
| | | img_result = np.where(img_result, img_result, img_bg) |
| | | |
| | | if aug is not None: |
| | | img_result = aug.augment_image(img_result) |
| | | |
| | | if display: |
| | | cv2.imshow('Result', img_result) |
| | | cv2.waitKey(0) |
| | | |
| | | self.img_result = img_result |
| | | pass |
| | | |
| | | def generate_horizontal_span(self, gap=None, scale=None, theta=0, shift=None, jitter=None): |
| | | """ |
| | | Generating the first scenario where the cards are laid out in a straight horizontal line |
| | | :return: True if successfully generated, otherwise False |
| | | """ |
| | | # Set scale of the cards, variance of shift & jitter to be applied if they're not given |
| | | card_size = (len(self.cards[0].img[0]), len(self.cards[0].img)) |
| | | if scale is None: |
| | | # Scale the cards so that card takes about 50% of the image's height |
| | | coverage_ratio = 0.5 |
| | | scale = self.height * coverage_ratio / card_size[1] |
| | | if shift is None: |
| | | # Plus minus 5% of the card's height |
| | | shift = [-card_size[1] * scale * 0.05, card_size[1] * scale * 0.05] |
| | | pass |
| | | if jitter is None: |
| | | jitter = [-math.pi / 18, math.pi / 18] # Plus minus 10 degrees |
| | | if gap is None: |
| | | # 25% of the card's width - set symbol and 1-2 mana symbols will be visible on each card |
| | | gap = card_size[0] * scale * 0.4 |
| | | |
| | | # Determine the location of the first card |
| | | # The cards will cover (width of a card + (# of cards - 1) * gap) pixels wide and (height of a card) pixels high |
| | | x_anchor = int(self.width / 2 + (len(self.cards) - 1) * gap / 2) |
| | | y_anchor = self.height // 2 |
| | | for card in self.cards: |
| | | card.scale = scale |
| | | card.x = x_anchor |
| | | card.y = y_anchor |
| | | card.theta = 0 |
| | | card.shift(shift, shift) |
| | | card.rotate(jitter) |
| | | card.rotate(theta, centre=(self.width // 2 - x_anchor, self.height // 2 - y_anchor)) |
| | | x_anchor -= gap |
| | | |
| | | return True |
| | | |
| | | def generate_vertical_span(self, gap=None, scale=None, theta=0, shift=None, jitter=None): |
| | | """ |
| | | Generating the second scenario where the cards are laid out in a straight vertical line |
| | | :return: True if successfully generated, otherwise False |
| | | """ |
| | | # Set scale of the cards, variance of shift & jitter to be applied if they're not given |
| | | card_size = (len(self.cards[0].img[0]), len(self.cards[0].img)) |
| | | if scale is None: |
| | | # Scale the cards so that card takes about 50% of the image's height |
| | | coverage_ratio = 0.5 |
| | | scale = self.height * coverage_ratio / card_size[1] |
| | | if shift is None: |
| | | # Plus minus 5% of the card's height |
| | | shift = [-card_size[1] * scale * 0.05, card_size[1] * scale * 0.05] |
| | | pass |
| | | if jitter is None: |
| | | # Plus minus 5 degrees |
| | | jitter = [-math.pi / 36, math.pi / 36] |
| | | if gap is None: |
| | | # 15% of the card's height - the title bar (with mana symbols) will be visible |
| | | gap = card_size[1] * scale * 0.25 |
| | | |
| | | # Determine the location of the first card |
| | | # The cards will cover (width of a card) pixels wide and (height of a card + (# of cards - 1) * gap) pixels high |
| | | x_anchor = self.width // 2 |
| | | y_anchor = int(self.height / 2 - (len(self.cards) - 1) * gap / 2) |
| | | for card in self.cards: |
| | | card.scale = scale |
| | | card.x = x_anchor |
| | | card.y = y_anchor |
| | | card.theta = 0 |
| | | card.shift(shift, shift) |
| | | card.rotate(jitter) |
| | | card.rotate(theta, centre=(self.width // 2 - x_anchor, self.height // 2 - y_anchor)) |
| | | y_anchor += gap |
| | | return True |
| | | |
| | | def generate_fan_out(self, centre, theta_between_cards=None, scale=None, shift=None, jitter=None): |
| | | """ |
| | | Generating the third scenario where the cards are laid out in a fan shape |
| | | :return: True if successfully generated, otherwise False |
| | | """ |
| | | return False |
| | | |
| | | def generate_non_obstructive(self, tolerance=0.90, scale=None): |
| | | """ |
| | | Generating the fourth scenario where the cards are laid in arbitrary position that doesn't obstruct other cards |
| | | :param tolerance: minimum level of visibility for each cards |
| | | :return: True if successfully generated, otherwise False |
| | | """ |
| | | card_size = (len(self.cards[0].img[0]), len(self.cards[0].img)) |
| | | if scale is None: |
| | | # Total area of the cards should cover about 25-40% of the entire image, depending on the number of cards |
| | | scale = math.sqrt(self.width * self.height * min(0.25 + 0.02 * len(self.cards), 0.4) |
| | | / (card_size[0] * card_size[1] * len(self.cards))) |
| | | # Position each card at random location that doesn't obstruct other cards |
| | | i = 0 |
| | | while i < len(self.cards): |
| | | #for i in range(len(self.cards)): |
| | | card = self.cards[i] |
| | | card.scale = scale |
| | | rep = 0 |
| | | while True: |
| | | card.x = random.uniform(card_size[1] * scale / 2, self.width - card_size[1] * scale) |
| | | card.y = random.uniform(card_size[1] * scale / 2, self.height - card_size[1] * scale) |
| | | card.theta = random.uniform(-math.pi, math.pi) |
| | | self.check_visibility(self.cards[:i + 1], visibility=tolerance) |
| | | # This position is not obstructive if all of the cards are visible |
| | | is_visible = [other_card.objects[0].visible for other_card in self.cards[:i + 1]] |
| | | non_obstructive = all(is_visible) |
| | | if non_obstructive: |
| | | i += 1 |
| | | break |
| | | rep += 1 |
| | | if rep >= 1000: |
| | | # Reassign previous card's position |
| | | i -= 1 |
| | | break |
| | | return True |
| | | |
| | | def check_visibility(self, cards=None, i_check=None, visibility=0.5): |
| | | """ |
| | | Check whether if extracted objects in each card are visible in the current scenario, and update their status |
| | | :param cards: list of cards (in a correct order) |
| | | :param i_check: indices of cards that needs to be checked. Cards that aren't in this list will only be used |
| | | to check visibility of other cards. All cards are checked by default. |
| | | :param visibility: minimum ratio of the object's area that aren't covered by another card to be visible |
| | | :return: none |
| | | """ |
| | | if cards is None: |
| | | cards = self.cards |
| | | if i_check is None: |
| | | i_check = range(len(cards)) |
| | | card_poly_list = [geometry.Polygon([card.coordinate_in_generator(0, 0), |
| | | card.coordinate_in_generator(0, len(card.img)), |
| | | card.coordinate_in_generator(len(card.img[0]), len(card.img)), |
| | | card.coordinate_in_generator(len(card.img[0]), 0)]) for card in self.cards] |
| | | template_poly = geometry.Polygon([(0, 0), (self.width, 0), (self.width, self.height), (0, self.height)]) |
| | | |
| | | # First card in the list is overlaid on the bottom of the card pile |
| | | for i in i_check: |
| | | card = cards[i] |
| | | for ext_obj in card.objects: |
| | | obj_poly = geometry.Polygon([card.coordinate_in_generator(pt[0], pt[1]) for pt in ext_obj.key_pts]) |
| | | obj_area = obj_poly.area |
| | | # Check if the other cards are blocking this object or if it's out of the template |
| | | for card_poly in card_poly_list[i + 1:]: |
| | | obj_poly = obj_poly.difference(card_poly) |
| | | obj_poly = obj_poly.intersection(template_poly) |
| | | visible_area = obj_poly.area |
| | | #print(visible_area, obj_area, len(card.img[0]) * len(card.img) * card.scale * card.scale) |
| | | #print("%s: %.1f visible" % (ext_obj.label, visible_area / obj_area * 100)) |
| | | ext_obj.visible = obj_area * visibility <= visible_area |
| | | |
| | | def export_training_data(self, out_name, visibility=0.5, aug=None): |
| | | """ |
| | | Export the generated training image along with the txt file for all bounding boxes |
| | | :return: none |
| | | """ |
| | | self.render(visibility, aug=aug) |
| | | cv2.imwrite(out_name + '.jpg', self.img_result) |
| | | out_txt = open(out_name+ '.txt', 'w') |
| | | for card in self.cards: |
| | | for ext_obj in card.objects: |
| | | if not ext_obj.visible: |
| | | continue |
| | | coords_in_gen = [card.coordinate_in_generator(key_pt[0], key_pt[1]) for key_pt in ext_obj.key_pts] |
| | | obj_yolo_info = key_pts_to_yolo(coords_in_gen, self.width, self.height) |
| | | if ext_obj.label == 'card': |
| | | class_id = self.class_ids[card.info['name']] |
| | | out_txt.write(str(class_id) + ' %.6f %.6f %.6f %.6f\n' % obj_yolo_info) |
| | | pass |
| | | elif ext_obj.label[:ext_obj.label.find[':']] == 'mana_symbol': |
| | | # TODO |
| | | pass |
| | | elif ext_obj.label[:ext_obj.label.find[':']] == 'set_symbol': |
| | | # TODO |
| | | pass |
| | | out_txt.close() |
| | | pass |
| | | |
| | | |
| | | class Card: |
| | | """ |
| | | A class for storing required information about a card in relation to the ImageGenerator |
| | | """ |
| | | def __init__(self, img, card_info, objects, x=None, y=None, theta=None, scale=None): |
| | | """ |
| | | :param img: image of the card |
| | | :param card_info: details like name, mana cost, type, set, etc |
| | | :param objects: list of ExtractedObjects like mana & set symbol, etc |
| | | :param generator: ImageGenerator object that the card is bound to |
| | | :param x: X-coordinate of the card's centre in relation to the generator |
| | | :param y: Y-coordinate of the card's centre in relation to the generator |
| | | :param theta: angle of rotation of the card in relation to the generator |
| | | :param scale: scale of the card in the generator in relation to the original image |
| | | """ |
| | | self.img = img |
| | | self.info = card_info |
| | | self.objects = objects |
| | | self.x = x |
| | | self.y = y |
| | | self.theta = theta |
| | | self.scale = scale |
| | | pass |
| | | |
| | | def shift(self, x, y): |
| | | """ |
| | | Apply a X/Y translation on this image |
| | | :param x: amount of X-translation. If range is given, translate by a random amount within that range |
| | | :param y: amount of Y-translation. Refer to x when a range is given. |
| | | :return: none |
| | | """ |
| | | if isinstance(x, tuple) or (isinstance(x, list) and len(x) == 2): |
| | | self.x += random.uniform(x[0], x[1]) |
| | | else: |
| | | self.x += x |
| | | if isinstance(y, tuple) or (isinstance(y, list) and len(y) == 2): |
| | | self.y += random.uniform(y[0], y[1]) |
| | | else: |
| | | self.y += y |
| | | pass |
| | | |
| | | def rotate(self, theta, centre=(0, 0)): |
| | | """ |
| | | Apply a rotation on this image with a centre |
| | | :param theta: amount of rotation in radian (clockwise). If a range is given, rotate by a random amount within |
| | | :param centre: coordinate of the centre of the rotation in relation to the centre of this card |
| | | that range |
| | | :return: none |
| | | """ |
| | | if isinstance(theta, tuple) or (isinstance(theta, list) and len(theta) == 2): |
| | | theta = random.uniform(theta[0], theta[1]) |
| | | |
| | | # If the centre given is the centre of this card, the whole math simplifies a bit |
| | | # (This still works without the if statement, but let's not do useless trigs if we know the answer already) |
| | | if centre is not (0, 0): |
| | | # Rotation math |
| | | self.x -= -centre[1] * math.sin(theta) + centre[0] * math.cos(theta) |
| | | self.y -= centre[1] * math.cos(theta) + centre[0] * math.sin(theta) |
| | | |
| | | # Offset for the coordinate translation |
| | | self.x += centre[0] |
| | | self.y += centre[1] |
| | | |
| | | self.theta += theta |
| | | pass |
| | | |
| | | def coordinate_in_generator(self, x, y): |
| | | """ |
| | | Converting coordinate within the card into the coordinate in the generator it is associated with |
| | | :param x: x coordinate within the card |
| | | :param y: y coordinate within the card |
| | | :return: (x, y) coordinate in the generator |
| | | """ |
| | | # Relative distance in X & Y axis, if the centre of the card is at the origin (0, 0) |
| | | rel_x = x - len(self.img[0]) // 2 |
| | | rel_y = y - len(self.img) // 2 |
| | | |
| | | # Scaling |
| | | rel_x *= self.scale |
| | | rel_y *= self.scale |
| | | |
| | | # Rotation |
| | | rot_x = rel_x - rel_y * math.sin(self.theta) + rel_x * math.cos(self.theta) |
| | | rot_y = rel_y + rel_y * math.cos(self.theta) + rel_x * math.sin(self.theta) |
| | | |
| | | # Negate offset |
| | | rot_x -= rel_x |
| | | rot_y -= rel_y |
| | | |
| | | # Shift |
| | | gen_x = rot_x + self.x |
| | | gen_y = rot_y + self.y |
| | | |
| | | return int(gen_x), int(gen_y) |
| | | |
| | | def bb_in_generator(self, key_pts): |
| | | """ |
| | | Convert a keypoints of bounding box in card into the coordinate in the generator |
| | | :param key_pts: keypoints of the bounding box |
| | | :return: bounding box represented by 4 points in the generator |
| | | """ |
| | | coords_in_gen = [self.coordinate_in_generator(key_pt[0], key_pt[1]) for key_pt in key_pts] |
| | | x1 = min([pt[0] for pt in coords_in_gen]) |
| | | x2 = max([pt[0] for pt in coords_in_gen]) |
| | | y1 = min([pt[1] for pt in coords_in_gen]) |
| | | y2 = max([pt[1] for pt in coords_in_gen]) |
| | | ''' |
| | | x1 = -math.inf |
| | | x2 = math.inf |
| | | y1 = -math.inf |
| | | y2 = math.inf |
| | | for key_pt in key_pts: |
| | | coord_in_gen = self.coordinate_in_generator(key_pt[0], key_pt[1]) |
| | | x1 = max(x1, coord_in_gen[0]) |
| | | x2 = min(x2, coord_in_gen[0]) |
| | | y1 = max(y1, coord_in_gen[1]) |
| | | y2 = min(y2, coord_in_gen[1]) |
| | | ''' |
| | | return [(x1, y1), (x2, y1), (x2, y2), (x1, y2)] |
| | | |
| | | |
| | | class ExtractedObject: |
| | | """ |
| | | Simple struct to hold information about an extracted object |
| | | """ |
| | | def __init__(self, label, key_pts): |
| | | self.label = label |
| | | self.key_pts = key_pts |
| | | self.visible = False |
| | | |
| | | |
| | | def main(): |
| | | random.seed() |
| | | ia.seed(random.randrange(10000)) |
| | | |
| | | bg_images = generate_data.load_dtd(dtd_dir='%s/dtd/images' % data_dir, dump_it=False) |
| | | #bg_images = [cv2.imread('data/frilly_0007.jpg')] |
| | | background = generate_data.Backgrounds(images=bg_images) |
| | | |
| | | #card_pool = pd.DataFrame() |
| | | #for set_name in fetch_data.all_set_list: |
| | | # df = fetch_data.load_all_cards_text('%s/csv/%s.csv' % (data_dir, set_name)) |
| | | # card_pool = card_pool.append(df) |
| | | card_pool = fetch_data.load_all_cards_text('%s/csv/custom.csv' % data_dir) |
| | | class_ids = {} |
| | | with open('%s/obj.names' % data_dir) as names_file: |
| | | class_name_list = names_file.read().splitlines() |
| | | for i in range(len(class_name_list)): |
| | | class_ids[class_name_list[i]] = i |
| | | print(class_ids) |
| | | |
| | | num_gen = 60000 |
| | | num_iter = 1 |
| | | |
| | | for i in range(num_gen): |
| | | # Arbitrarily select top left and right corners for perspective transformation |
| | | # Since the training image are generated with random rotation, don't need to skew all four sides |
| | | skew = [[random.uniform(0, 0.25), 0], [0, 1], [1, 1], |
| | | [random.uniform(0.75, 1), 0]] |
| | | generator = ImageGenerator(background.get_random(), class_ids, 1440, 960, skew=skew) |
| | | out_name = '' |
| | | for _, card_info in card_pool.sample(random.randint(2, 5)).iterrows(): |
| | | img_name = '%s/card_img/png/%s/%s_%s.png' % (data_dir, card_info['set'], card_info['collector_number'], |
| | | fetch_data.get_valid_filename(card_info['name'])) |
| | | out_name += '%s%s_' % (card_info['set'], card_info['collector_number']) |
| | | card_img = cv2.imread(img_name) |
| | | if card_img is None: |
| | | fetch_data.fetch_card_image(card_info, out_dir='%s/card_img/png/%s' % (data_dir, card_info['set'])) |
| | | card_img = cv2.imread(img_name) |
| | | if card_img is None: |
| | | print('WARNING: card %s is not found!' % img_name) |
| | | detected_object_list = generate_data.apply_bounding_box(card_img, card_info) |
| | | card = Card(card_img, card_info, detected_object_list) |
| | | generator.add_card(card) |
| | | for j in range(num_iter): |
| | | seq = iaa.Sequential([ |
| | | iaa.Multiply((0.8, 1.2)), # darken / brighten the whole image |
| | | iaa.SimplexNoiseAlpha(first=iaa.Add(random.randrange(64)), per_channel=0.1, size_px_max=[3, 6], |
| | | upscale_method="cubic"), # Lighting |
| | | iaa.AdditiveGaussianNoise(scale=random.uniform(0, 0.05) * 255, per_channel=0.1), # Noises |
| | | iaa.Dropout(p=[0, 0.05], per_channel=0.1) |
| | | ]) |
| | | |
| | | if i % 3 == 0: |
| | | generator.generate_non_obstructive() |
| | | generator.export_training_data(visibility=0.0, out_name='%s/train/non_obstructive_10/%s%d' |
| | | % (data_dir, out_name, j), aug=seq) |
| | | elif i % 3 == 1: |
| | | generator.generate_horizontal_span(theta=random.uniform(-math.pi, math.pi)) |
| | | generator.export_training_data(visibility=0.0, out_name='%s/train/horizontal_span_10/%s%d' |
| | | % (data_dir, out_name, j), aug=seq) |
| | | else: |
| | | generator.generate_vertical_span(theta=random.uniform(-math.pi, math.pi)) |
| | | generator.export_training_data(visibility=0.0, out_name='%s/train/vertical_span_10/%s%d' |
| | | % (data_dir, out_name, j), aug=seq) |
| | | |
| | | #generator.generate_horizontal_span(theta=random.uniform(-math.pi, math.pi)) |
| | | #generator.render(display=True, aug=seq, debug=True) |
| | | print('Generated %s%d' % (out_name, j)) |
| | | generator.img_bg = background.get_random() |
| | | pass |
| | | |
| | | |
| | | if __name__ == '__main__': |
| | | main() |