From 6227a8da1770de3eb09e220d3330c21c00dd97ba Mon Sep 17 00:00:00 2001
From: Constantin Wenger <constantin.wenger@googlemail.com>
Date: Tue, 13 Aug 2019 20:41:25 +0000
Subject: [PATCH] work a round for "con" being a forbidden filename on windows
---
transform_data.py | 67 ++++++++++++++++++---------------
1 files changed, 36 insertions(+), 31 deletions(-)
diff --git a/transform_data.py b/transform_data.py
index 6b5f477..f4fa1a9 100644
--- a/transform_data.py
+++ b/transform_data.py
@@ -1,20 +1,19 @@
-import os
-import random
-import math
+import argparse
import cv2
-import numpy as np
-import imutils
-import pandas as pd
-import fetch_data
-import generate_data
-from shapely import geometry
import imgaug as ia
from imgaug import augmenters as iaa
from imgaug import parameters as iap
+import imutils
+import math
+import numpy as np
+import os
+import pandas as pd
+import random
+from shapely import geometry
-card_mask = cv2.imread('data/mask.png')
-data_dir = os.path.abspath('/media/win10/data')
-darknet_dir = os.path.abspath('.')
+import fetch_data
+import generate_data
+from config import Config
def key_pts_to_yolo(key_pts, w_img, h_img):
@@ -104,6 +103,7 @@
"""
self.check_visibility(visibility=visibility)
img_result = np.zeros((self.height, self.width, 3), dtype=np.uint8)
+ card_mask = cv2.imread(Config.card_mask_path)
for card in self.cards:
card_x = int(card.x + 0.5)
@@ -490,44 +490,41 @@
self.visible = False
-def main():
+def main(args):
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 = generate_data.load_dtd(dtd_dir='%s/dtd/images' % Config.data_dir, dump_it=False)
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))
+ for set_name in Config.all_set_list:
+ df = fetch_data.load_all_cards_text('%s/csv/%s.csv' % (Config.data_dir, set_name))
card_pool = card_pool.append(df)
class_ids = {}
- with open('%s/obj.names' % data_dir) as names_file:
+ with open('%s/obj.names' % Config.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
- num_gen = 60000
- num_iter = 1
- w_gen = 1440
- h_gen = 960
-
- for i in range(num_gen):
+ for i in range(args.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, w_gen, h_gen, skew=skew)
+ generator = ImageGenerator(background.get_random(), class_ids, args.width, args.height, skew=skew)
out_name = ''
# Use 2 to 5 cards per generator
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'],
+ img_name = '%s/card_img/png/%s/%s_%s.png' % (Config.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']))
+ fetch_data.fetch_card_image(card_info, out_dir='%s/card_img/png/%s' % (Config.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)
@@ -535,7 +532,7 @@
card = Card(card_img, card_info, detected_object_list)
generator.add_card(card)
- for j in range(num_iter):
+ for j in range(args.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],
@@ -547,15 +544,15 @@
if i % 3 == 0:
generator.generate_non_obstructive()
generator.export_training_data(visibility=0.0, out_name='%s/train/non_obstructive_update/%s%d'
- % (data_dir, out_name, j), aug=seq)
+ % (Config.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_update/%s%d'
- % (data_dir, out_name, j), aug=seq)
+ % (Config.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_update/%s%d'
- % (data_dir, out_name, j), aug=seq)
+ % (Config.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)
@@ -565,4 +562,12 @@
if __name__ == '__main__':
- main()
+ parser = argparse.ArgumentParser()
+ parser.add_argument('-n', '--num_gen', dest='num_gen', help='Number of training images to generate',
+ type=int, required=True)
+ parser.add_argument('-ni', '--num_iter', dest='num_iter', help='Number of iterations to generate each config',
+ type=int, default=1)
+ parser.add_argument('-w', '--width', dest='width', help='Width of the training image', type=int, default=1440)
+ parser.add_argument('-ht', '--height', dest='height', help='Height of the training image', type=int, default=960)
+ args = parser.parse_args()
+ main(args)
--
Gitblit v1.10.0