More testing stuffs

Edmond Yoo

2018-09-08 62084d6733a78822f39dd8a1fe01c77eea281a65

More testing stuffs

 data/test1.mp4

Binary files differ

 data/test10.jpg

 data/test11.jpg

 data/test12.jpg

 data/test13.jpg

 data/test14.jpg

 data/test15.jpg

 data/test16.jpg

 data/test17.jpg

 data/test18.jpg

 data/test19.jpg

 data/test2.mp4

Binary files differ

 data/test20.jpg

 data/test21.jpg

 data/test7.jpg

 data/test8.jpg

 data/test9.jpg

 generate_data.py

@@ -11,7 +11,7 @@
import sys
import numpy as np
import pandas as pd
from transform_data import ExtractedObject
import transform_data

# Referenced from geaxgx's playing-card-detection: https://github.com/geaxgx/playing-card-detection
class Backgrounds:
@@ -66,7 +66,7 @@
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 = [ExtractedObject('card', [(0, 0), (len(img[0]), 0), (len(img[0]), len(img)), (0, len(img))])]
    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.
@@ -98,7 +98,7 @@
            # 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(ExtractedObject(symbol_name, key_pts))
            detected_object_list.append(transform_data.ExtractedObject(symbol_name, key_pts))

            if display:
                img_symbol = img[y1:y2, x1:x2]
@@ -163,7 +163,7 @@
    # 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(ExtractedObject(symbol_name, key_pts))
    detected_object_list.append(transform_data.ExtractedObject(symbol_name, key_pts))

    if display:
        img_symbol = img[y1:y2, x1:x2]

 setup_train.py

@@ -1,13 +1,13 @@
import os
from glob import glob
import random
from transform_data import data_dir, darknet_dir
import transform_data


def main():
    random.seed()
    data_list = []
    for subdir in glob('%s/train/*' % data_dir):
    for subdir in glob('%s/train/*' % transform_data.data_dir):
        for data in glob(subdir + "/*.jpg"):
            data_list.append(os.path.abspath(data))
    random.shuffle(data_list)
@@ -15,10 +15,10 @@
    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.txt' % darknet_dir, 'w') as train_txt:
    with open('%s/train.txt' % transform_data.darknet_dir, 'w') as train_txt:
        for data in train_list:
            train_txt.write(data + '\n')
    with open('%s/test.txt' % darknet_dir, 'w') as test_txt:
    with open('%s/test.txt' % transform_data.darknet_dir, 'w') as test_txt:
        for data in test_list:
            test_txt.write(data + '\n')
    return

 transform_data.py

@@ -14,7 +14,7 @@
from imgaug import parameters as iap

card_mask = cv2.imread('data/mask.png')
data_dir = os.path.abspath('/media/edmond/My Passport/data')
data_dir = os.path.abspath('/media/win10/data')
darknet_dir = os.path.abspath('darknet')


@@ -529,15 +529,15 @@
            ])
            if i % 3 == 0:
                generator.generate_non_obstructive()
                generator.export_training_data(visibility=0.0, out_name='%s/train/non_obstructive/%s_%d'
                generator.export_training_data(visibility=0.0, out_name='%s/train/non_obstructive_skew/%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/%s_%d'
                generator.export_training_data(visibility=0.0, out_name='%s/train/horizontal_span_skew/%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/%s_%d'
                generator.export_training_data(visibility=0.0, out_name='%s/train/vertical_span_skew/%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)