def __getitem__(self, i):
random_seed = random.randint(0, 3)
random_seed = self.filp_dict[random_seed]
data = self.data[i]
img = cv2.imread(data[0])
mask = np.zeros_like(img[:, :, 0])
if data[1]:
mask = gif2numpy.convert(data[1])
mask = mask[0][0]
# mask_out = mask[:, :, 0] == 255
mask_out = np.zeros_like(mask[:, :, 0])
mask_out[mask[:, :, 0] == 255] = 1
mask = mask_out
# if self.set_mode=='train':
# mask = self.process_data(mask,random_seed)
# mask = mask[224:448,224:448]
# img = self.preprocess(img, self.scale)
# mask = self.preprocess(mask, self.scale)
# img= img[224:448,224:448,:]
# img_out = img
# img = self.process_data(img,random_seed)
img_out = cv2.resize(img, (448, 448))
# cv2.imshow('a',img_out)
# cv2.waitKey()
# cv2.destroyAllWindows()
img_out = img_out / 255
# mean = (img_out).mean((0,1))
# img_out = img_out - mean
return {
'image': torch.from_numpy(img_out).permute((2, 0, 1)),
'mask': torch.from_numpy(np.array(mask)),
'o_s': img.shape[:2]
}
def analyze_color(image_path):
if not image_path.endswith('.gif'):
im = cv2.imread(image_path)
else:
np_images, extensions, image_specs = gif2numpy.convert(image_path)
im = np_images[0]
distinct_colors = set(tuple(v) for m2d in im for v in m2d)
color_dict[image_path] = len(distinct_colors)
def get_all(self):
data = []
mm = []
for d in self.data:
img = cv2.imread(d[0])
if data[1]:
mask = gif2numpy.convert(d[1])
mask = mask[0][0]
mask = mask[:, :, 0] == 255
mm.append(mask)
data.append(img)
data = np.array(data)
mm = np.array(mm)
return data, mm
def getImages(directorypath):
os.chdir(directorypath)
images = []
# Gather the images in the file path
for file in glob.glob("*"):
# cv2 doesn't suppoer gif so we are converting all gifs to be numpy compatible
if file.endswith(".gif"):
frames, extensions, image_specs = gif2numpy.convert(file)
image = frames[0]
else:
image = cv2.imread(file, 1)
images.append(image)
# Resize images to be the same size as the first
width = int(0.6 * images[0].shape[1])
height = int(0.6 * images[0].shape[0])
dim = (width, height)
for i, img in enumerate(images):
images[i] = cv2.resize(img, dim, interpolation=cv2.INTER_AREA)
return images
def testGenerator(test_image_path, test_label_path, img_size, img_shape):
# read the list of test image in dir
image_list = os.listdir(test_image_path)
image_list = sorted(image_list)
print(image_list)
test_test_data = []
test_label_data = []
for img_name in image_list:
#print(test_image_path+img_name)
img = cv2.imread(test_image_path + img_name, 1)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# resize to 512, 512
img = cv2.resize(img, img_size)
img = img.astype('float32')
img = img / 255.
img = np.reshape(img, img_shape)
test_test_data.append(img)
label_list = os.listdir(test_label_path)
label_list = sorted(label_list)
print(label_list)
for img_name in label_list:
# read gif image
np_frames, extensions, img_spec = gif2numpy.convert(test_label_path +
img_name)
#img = cv2.imread(test_label_path+img_name,1)
#img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# resize to 512, 512
#img = cv2.resize(img,img_size)
img = cv2.resize(np_frames[0], img_size)
#img = img.astype('float32')
img = img / 255.
img = img[:, :, 0]
img = np.reshape(img, img_shape)
test_label_data.append(img)
return ([test_test_data, test_label_data])
# cv2.waitKey()
#
# cv2.destroyAllWindows()
return image_segmented
if __name__ == '__main__':
output_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'extras')
data_path = glob.glob(os.path.join(os.path.dirname(__file__), 'data', '*'))
data = {}
for d in data_path:
if 'manual1' in d:
gif = gif2numpy.convert(d)
continue
elif '02' not in d:
continue
data[d.split('/')[-1]] = cv2.imread(d)
print(d)
img = list(data.values())[0]
# cv2.imshow('Origin', img)
# cv2.waitKey()
# cv2.destroyAllWindows()
res = seg(img)
cv2.imwrite(os.path.join(output_dir, 'fused_res_02.jpg'), res)
pass
import gif2numpy
import numpy as np
import cv2
np_frame, extenstions, image_spec = gif2numpy.convert("white.gif")
#for fram in np_frame:
s = ""
l = ""
board = np.zeros(shape=(100, 100, 3))
x = 50
y = 50
i = 0
boards = []
for frame in np_frame:
out = False
for row, r in zip(frame, range(len(frame))):
for col, c in zip(row, range(len(row))):
if (not (out) and all(x == 8 for x in col)):
if (r == 100 and c == 100):
i += 1
boards.append(board)
board = np.zeros(shape=(100, 100, 3))
x = 50
y = 50
out = True
if (r == 100 and c == 102):
x += 1
if (r == 102 and c == 100):
y += 1
if (r == 102 and c == 102):
x += 1
y += 1
def main(dir: str):
checker = language_tool_python.LanguageTool('en-US')
emails = {}
totalWords = ''
filenames = [
filename for filename in os.listdir(dir) if filename.endswith('.eml')
]
for filename in filenames:
print()
print('[INFO] Processing {}...'.format(filename))
with open(os.path.join(dir, filename), 'r', encoding='latin1') as file:
try:
mail = mailparser.parse_from_file_obj(file)
except Exception as e:
print('[WARNING] Error while parsing: {}'.format(e))
continue
# filter duplicates based on subject
#if mail.subject in emails:
# print('[WARNING] This email seems to be a duplicate of "{}"! Skipping...'
# .format(emails[mail.subject]['filename']))
# continue
# don't process if auth results missing
# if 'Authentication-Results' not in mail.headers:
# print('[WARNING] This email is missing an authentication results header! Skipping...')
# continue
attachments = ''
for attachment in mail.attachments:
attachment['filename'] = re.sub(r'<|>', '',
attachment['filename'])
try:
mail.write_attachments(dir)
for attachment in mail.attachments:
if re.search('image', attachment['mail_content_type']):
if re.search('gif', attachment['mail_content_type']):
images, _, _ = gif2numpy.convert(
dir + '\\' + attachment['filename'])
img = images[0]
else:
img = cv2.imread(dir + '\\' +
attachment['filename'])
img = cv2.resize(img,
None,
fx=1.2,
fy=1.2,
interpolation=cv2.INTER_CUBIC)
text = pytesseract.image_to_string(img)
attachments += text
elif re.search('pdf', attachment['mail_content_type']):
encoding = chardet.detect(
pdf_to_text(dir + '\\' +
attachment['filename']))['encoding']
attachments += pdf_to_text(
dir + '\\' +
attachment['filename']).decode(encoding)
# elif re.search('text', attachment['mail_content_type']):
# #print(chardet.detect((attachment['payload']).encode()))
# #encoding = chardet.detect(base64.b64decode(attachment['payload']).encode())['encoding']
# #attachments += base64.b64decode(attachment['payload']).decode(encoding)
# #print(codecs.encode(base64.b64decode(attachment['payload']), encoding=attachment['content_transfer_encoding']))
# attachments += attachment['payload']
else:
attachments += attachment['payload']
os.remove(dir + '\\' + attachment['filename'])
except Exception as e:
print(
'[WARNING] Error while parsing attachments: {}'.format(e))
[
os.remove(dir + '\\' + attachment['filename'])
for attachment in mail.attachments
]
body = mail.subject + ' ' + \
remove_noise(BeautifulSoup(mail.body, 'lxml').get_text(separator=' ', strip=True) +
BeautifulSoup(attachments, 'lxml').get_text())
blob = TextBlob(body)
totalWords = totalWords + " " + body.lower()
grammarErrors = checker.check(body)
if 'Authentication-Results' in mail.headers:
spf = re.findall('spf=(\S*)',
mail.headers['Authentication-Results'])
dkim = re.findall('dkim=(\S*)',
mail.headers['Authentication-Results'])
dmarc = re.findall('dmarc=(\S*)',
mail.headers['Authentication-Results'])
else:
spf = dkim = dmarc = ''
emails[filename] = {
'filename': filename,
# 'hops': mail.received[-1]['hop'],
# 'totalDelay': sum([hop['delay']/60 for hop in mail.received]),
'spf': spf[0] if len(spf) else None,
'dkim': dkim[0] if len(dkim) else None,
'dmarc': dmarc[0] if len(dmarc) else None,
'subject': mail.subject,
'from': mail.from_[0][1],
'to': [tup[1] for tup in mail.to],
'replyTo': [tup[1] for tup in mail.reply_to],
'attachments': [x['filename'] for x in mail.attachments],
'grammarErrors': len(grammarErrors),
'counts': {
'characterCount': len(body),
'wordCount': textstat.lexicon_count(body),
'sentenceCount': textstat.sentence_count(body)
},
'readability': {
'flesch_kincaid':
textstat.flesch_kincaid_grade(body),
'gunning_fog':
textstat.gunning_fog(body),
'smog_index':
textstat.smog_index(body),
'automated_readability_index':
textstat.automated_readability_index(body),
'coleman_liau_index':
textstat.coleman_liau_index(body),
'linsear_write':
textstat.linsear_write_formula(body),
},
'sentiment': {
'polarity': blob.sentiment.polarity,
'subjectivity': blob.sentiment.subjectivity
}
}
if save_body:
emails[filename]['body'] = body
## quit if nothing found ##
# if not emails:
# print('[WARNING] No files were found in "{}"!'.format(dir))
# return
## writing all words to file ##
with open(os.path.join(dir, 'words.txt'), 'w', encoding='utf-8') as file:
file.write(totalWords.lower())
## output json ##
with open(os.path.join(dir, 'analysis.json'), 'w') as jsonFile:
json.dump(emails, jsonFile, indent=2)
## build and output csv ##
# generate and output headers using first email
column_headers = list(flatten_json(emails[list(emails.keys())[0]]).keys())
csvFile = open(os.path.join(dir, 'analysis.csv'), 'w', encoding='utf-8')
csvFile.write(',{}\n'.format(','.join(column_headers)))
# generate and output one line per email
for email in emails.keys():
# flatten json to 1 layer deep
flattened_email = flatten_json(emails[email])
# generate the values for this row
csv_values = [
'"' + str(flattened_email[column_header]) + '"'
for column_header in column_headers
]
# add email name and join w/ commas, then write out
csvFile.write('{},{}\n'.format('"' + email + '"',
','.join(csv_values)))
csvFile.close()
# print out stats
print('{}/{} processed. The remaining failed for some reason.'.format(
len(emails), len(filenames)))
import gif2numpy
import cv2
import numpy as np
from PIL import Image
def rgb2gray(rgb):
r, g, b = rgb[:, :, 0], rgb[:, :, 1], rgb[:, :, 2]
gray = 0.2989 * r + 0.5870 * g + 0.1140 * b
return np.array(gray).astype('int')
np_frames, extensions, image_specifications = gif2numpy.convert("alphabet.gif")
img = np_frames[0]
for i in range(10):
#cv2.imshow(chr(65 + i), img[0:44, i*43:(i+1)*43+1, :])
cv2.imwrite(
chr(48 + (i + 1) % 10) + '.jpg', img[43 * 4:43 * 5 + 1,
i * 43:(i + 1) * 43 + 1, :])
cv2.waitKey()
cv2.destroyAllWindows()
def readGIF(path):
import gif2numpy
np_imgs, extensions, img_specs = gif2numpy.convert(path)
return np_imgs[0]
from __future__ import print_function
from gif2numpy import convert
from numpy2gif import write_gif
import cv2
image = "Images/Rotating_earth.gif"
frames, exts, image_specs = convert(image, BGR2RGB=False)
print("len(frames), len(exts), exts[0]['delay_time']", len(frames), len(exts), exts[0]['delay_time'])
write_gif(frames, 'Rotating_earth_new.gif', fps=12)
write_gif(frames[0], 'earth.gif')
from __future__ import print_function
import gif2numpy
import cv2
print(gif2numpy.version)
images = "Images/hopper.gif", "Images/audrey.gif", "Images/Rotating_earth.gif", "Images/testcolors.gif"
for image in images:
frames, exts, image_specs = gif2numpy.convert(image)
print()
print("Image:", image)
print()
print("len frames", len(frames))
print("len exts", len(exts))
print("exts:", exts)
print("image_specs:", image_specs)
for i in range(len(frames)):
cv2.imshow("np_image", frames[i])
print(exts[i])
k = cv2.waitKey(0)
if k == 27:
break
cv2.destroyWindow("np_image")
