Spaces:
Runtime error
Runtime error
File size: 15,410 Bytes
c310e19 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 |
#!/usr/bin/env python2
#encoding: UTF-8
import json
import sys;sys.path.append('./')
import zipfile
import re
import sys
import os
import codecs
import importlib
try:
from StringIO import StringIO
except ImportError:
from io import StringIO
def print_help():
sys.stdout.write('Usage: python %s.py -g=<gtFile> -s=<submFile> [-o=<outputFolder> -p=<jsonParams>]' %sys.argv[0])
sys.exit(2)
def load_zip_file_keys(file,fileNameRegExp=''):
"""
Returns an array with the entries of the ZIP file that match with the regular expression.
The key's are the names or the file or the capturing group definied in the fileNameRegExp
"""
try:
archive=zipfile.ZipFile(file, mode='r', allowZip64=True)
except :
raise Exception('Error loading the ZIP archive.')
pairs = []
for name in archive.namelist():
addFile = True
keyName = name
if fileNameRegExp!="":
m = re.match(fileNameRegExp,name)
if m == None:
addFile = False
else:
if len(m.groups())>0:
keyName = m.group(1)
if addFile:
pairs.append( keyName )
return pairs
def load_zip_file(file,fileNameRegExp='',allEntries=False):
"""
Returns an array with the contents (filtered by fileNameRegExp) of a ZIP file.
The key's are the names or the file or the capturing group definied in the fileNameRegExp
allEntries validates that all entries in the ZIP file pass the fileNameRegExp
"""
try:
archive=zipfile.ZipFile(file, mode='r', allowZip64=True)
except :
raise Exception('Error loading the ZIP archive')
pairs = []
for name in archive.namelist():
addFile = True
keyName = name
if fileNameRegExp!="":
m = re.match(fileNameRegExp,name)
if m == None:
addFile = False
else:
if len(m.groups())>0:
keyName = m.group(1)
if addFile:
pairs.append( [ keyName , archive.read(name)] )
else:
if allEntries:
raise Exception('ZIP entry not valid: %s' %name)
return dict(pairs)
def decode_utf8(raw):
"""
Returns a Unicode object on success, or None on failure
"""
try:
raw = codecs.decode(raw,'utf-8', 'replace')
#extracts BOM if exists
raw = raw.encode('utf8')
if raw.startswith(codecs.BOM_UTF8):
raw = raw.replace(codecs.BOM_UTF8, '', 1)
return raw.decode('utf-8')
except:
return None
def validate_lines_in_file(fileName,file_contents,CRLF=True,LTRB=True,withTranscription=False,withConfidence=False,imWidth=0,imHeight=0):
"""
This function validates that all lines of the file calling the Line validation function for each line
"""
utf8File = decode_utf8(file_contents)
if (utf8File is None) :
raise Exception("The file %s is not UTF-8" %fileName)
lines = utf8File.split( "\r\n" if CRLF else "\n" )
for line in lines:
line = line.replace("\r","").replace("\n","")
if(line != ""):
try:
validate_tl_line(line,LTRB,withTranscription,withConfidence,imWidth,imHeight)
except Exception as e:
raise Exception(("Line in sample not valid. Sample: %s Line: %s Error: %s" %(fileName,line,str(e))).encode('utf-8', 'replace'))
def validate_tl_line(line,LTRB=True,withTranscription=True,withConfidence=True,imWidth=0,imHeight=0):
"""
Validate the format of the line. If the line is not valid an exception will be raised.
If maxWidth and maxHeight are specified, all points must be inside the imgage bounds.
Posible values are:
LTRB=True: xmin,ymin,xmax,ymax[,confidence][,transcription]
LTRB=False: x1,y1,x2,y2,x3,y3,x4,y4[,confidence][,transcription]
"""
get_tl_line_values(line,LTRB,withTranscription,withConfidence,imWidth,imHeight)
def get_tl_line_values(line,LTRB=True,withTranscription=False,withConfidence=False,imWidth=0,imHeight=0):
"""
Validate the format of the line. If the line is not valid an exception will be raised.
If maxWidth and maxHeight are specified, all points must be inside the imgage bounds.
Posible values are:
LTRB=True: xmin,ymin,xmax,ymax[,confidence][,transcription]
LTRB=False: x1,y1,x2,y2,x3,y3,x4,y4[,confidence][,transcription]
Returns values from a textline. Points , [Confidences], [Transcriptions]
"""
confidence = 0.0
transcription = "";
points = []
numPoints = 4;
if LTRB:
numPoints = 4;
if withTranscription and withConfidence:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-1].?[0-9]*)\s*,(.*)$',line)
if m == None :
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-1].?[0-9]*)\s*,(.*)$',line)
raise Exception("Format incorrect. Should be: xmin,ymin,xmax,ymax,confidence,transcription")
elif withConfidence:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-1].?[0-9]*)\s*$',line)
if m == None :
raise Exception("Format incorrect. Should be: xmin,ymin,xmax,ymax,confidence")
elif withTranscription:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-9]+)\s*,(.*)$',line)
if m == None :
raise Exception("Format incorrect. Should be: xmin,ymin,xmax,ymax,transcription")
else:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-9]+)\s*,?\s*$',line)
if m == None :
raise Exception("Format incorrect. Should be: xmin,ymin,xmax,ymax")
xmin = int(m.group(1))
ymin = int(m.group(2))
xmax = int(m.group(3))
ymax = int(m.group(4))
if(xmax<xmin):
raise Exception("Xmax value (%s) not valid (Xmax < Xmin)." %(xmax))
if(ymax<ymin):
raise Exception("Ymax value (%s) not valid (Ymax < Ymin)." %(ymax))
points = [ float(m.group(i)) for i in range(1, (numPoints+1) ) ]
if (imWidth>0 and imHeight>0):
validate_point_inside_bounds(xmin,ymin,imWidth,imHeight);
validate_point_inside_bounds(xmax,ymax,imWidth,imHeight);
else:
numPoints = 8;
if withTranscription and withConfidence:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*([0-1].?[0-9]*)\s*,(.*)$',line)
if m == None :
raise Exception("Format incorrect. Should be: x1,y1,x2,y2,x3,y3,x4,y4,confidence,transcription")
elif withConfidence:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*([0-1].?[0-9]*)\s*$',line)
if m == None :
raise Exception("Format incorrect. Should be: x1,y1,x2,y2,x3,y3,x4,y4,confidence")
elif withTranscription:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,(.*)$',line)
if m == None :
raise Exception("Format incorrect. Should be: x1,y1,x2,y2,x3,y3,x4,y4,transcription")
else:
m = re.match(r'^\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*,\s*(-?[0-9]+)\s*$',line)
if m == None :
raise Exception("Format incorrect. Should be: x1,y1,x2,y2,x3,y3,x4,y4")
points = [ float(m.group(i)) for i in range(1, (numPoints+1) ) ]
validate_clockwise_points(points)
if (imWidth>0 and imHeight>0):
validate_point_inside_bounds(points[0],points[1],imWidth,imHeight);
validate_point_inside_bounds(points[2],points[3],imWidth,imHeight);
validate_point_inside_bounds(points[4],points[5],imWidth,imHeight);
validate_point_inside_bounds(points[6],points[7],imWidth,imHeight);
if withConfidence:
try:
confidence = float(m.group(numPoints+1))
except ValueError:
raise Exception("Confidence value must be a float")
if withTranscription:
posTranscription = numPoints + (2 if withConfidence else 1)
transcription = m.group(posTranscription)
m2 = re.match(r'^\s*\"(.*)\"\s*$',transcription)
if m2 != None : #Transcription with double quotes, we extract the value and replace escaped characters
transcription = m2.group(1).replace("\\\\", "\\").replace("\\\"", "\"")
return points,confidence,transcription
def validate_point_inside_bounds(x,y,imWidth,imHeight):
if(x<0 or x>imWidth):
raise Exception("X value (%s) not valid. Image dimensions: (%s,%s)" %(xmin,imWidth,imHeight))
if(y<0 or y>imHeight):
raise Exception("Y value (%s) not valid. Image dimensions: (%s,%s) Sample: %s Line:%s" %(ymin,imWidth,imHeight))
def validate_clockwise_points(points):
"""
Validates that the points that the 4 points that dlimite a polygon are in clockwise order.
"""
if len(points) != 8:
raise Exception("Points list not valid." + str(len(points)))
point = [
[int(points[0]) , int(points[1])],
[int(points[2]) , int(points[3])],
[int(points[4]) , int(points[5])],
[int(points[6]) , int(points[7])]
]
edge = [
( point[1][0] - point[0][0])*( point[1][1] + point[0][1]),
( point[2][0] - point[1][0])*( point[2][1] + point[1][1]),
( point[3][0] - point[2][0])*( point[3][1] + point[2][1]),
( point[0][0] - point[3][0])*( point[0][1] + point[3][1])
]
summatory = edge[0] + edge[1] + edge[2] + edge[3];
if summatory>0:
raise Exception("Points are not clockwise. The coordinates of bounding quadrilaterals have to be given in clockwise order. Regarding the correct interpretation of 'clockwise' remember that the image coordinate system used is the standard one, with the image origin at the upper left, the X axis extending to the right and Y axis extending downwards.")
def get_tl_line_values_from_file_contents(content,CRLF=True,LTRB=True,withTranscription=False,withConfidence=False,imWidth=0,imHeight=0,sort_by_confidences=True):
"""
Returns all points, confindences and transcriptions of a file in lists. Valid line formats:
xmin,ymin,xmax,ymax,[confidence],[transcription]
x1,y1,x2,y2,x3,y3,x4,y4,[confidence],[transcription]
"""
pointsList = []
transcriptionsList = []
confidencesList = []
lines = content.split( "\r\n" if CRLF else "\n" )
for line in lines:
line = line.replace("\r","").replace("\n","")
if(line != "") :
points, confidence, transcription = get_tl_line_values(line,LTRB,withTranscription,withConfidence,imWidth,imHeight);
pointsList.append(points)
transcriptionsList.append(transcription)
confidencesList.append(confidence)
if withConfidence and len(confidencesList)>0 and sort_by_confidences:
import numpy as np
sorted_ind = np.argsort(-np.array(confidencesList))
confidencesList = [confidencesList[i] for i in sorted_ind]
pointsList = [pointsList[i] for i in sorted_ind]
transcriptionsList = [transcriptionsList[i] for i in sorted_ind]
return pointsList,confidencesList,transcriptionsList
def main_evaluation(p,default_evaluation_params_fn,validate_data_fn,evaluate_method_fn,show_result=True,per_sample=True):
"""
This process validates a method, evaluates it and if it succed generates a ZIP file with a JSON entry for each sample.
Params:
p: Dictionary of parmeters with the GT/submission locations. If None is passed, the parameters send by the system are used.
default_evaluation_params_fn: points to a function that returns a dictionary with the default parameters used for the evaluation
validate_data_fn: points to a method that validates the corrct format of the submission
evaluate_method_fn: points to a function that evaluated the submission and return a Dictionary with the results
"""
if (p == None):
p = dict([s[1:].split('=') for s in sys.argv[1:]])
if(len(sys.argv)<3):
print_help()
evalParams = default_evaluation_params_fn()
if 'p' in p.keys():
evalParams.update( p['p'] if isinstance(p['p'], dict) else json.loads(p['p'][1:-1]) )
resDict={'calculated':True,'Message':'','method':'{}','per_sample':'{}'}
try:
validate_data_fn(p['g'], p['s'], evalParams)
evalData = evaluate_method_fn(p['g'], p['s'], evalParams)
resDict.update(evalData)
except Exception as e:
resDict['Message']= str(e)
resDict['calculated']=False
if 'o' in p:
if not os.path.exists(p['o']):
os.makedirs(p['o'])
resultsOutputname = p['o'] + '/results.zip'
outZip = zipfile.ZipFile(resultsOutputname, mode='w', allowZip64=True)
del resDict['per_sample']
if 'output_items' in resDict.keys():
del resDict['output_items']
outZip.writestr('method.json',json.dumps(resDict))
if not resDict['calculated']:
if show_result:
sys.stderr.write('Error!\n'+ resDict['Message']+'\n\n')
if 'o' in p:
outZip.close()
return resDict
if 'o' in p:
if per_sample == True:
for k,v in evalData['per_sample'].items():
outZip.writestr( k + '.json',json.dumps(v))
if 'output_items' in evalData.keys():
for k, v in evalData['output_items'].items():
outZip.writestr( k,v)
outZip.close()
if show_result:
sys.stdout.write("Calculated!")
sys.stdout.write(json.dumps(resDict['method']))
return resDict
def main_validation(default_evaluation_params_fn,validate_data_fn):
"""
This process validates a method
Params:
default_evaluation_params_fn: points to a function that returns a dictionary with the default parameters used for the evaluation
validate_data_fn: points to a method that validates the corrct format of the submission
"""
try:
p = dict([s[1:].split('=') for s in sys.argv[1:]])
evalParams = default_evaluation_params_fn()
if 'p' in p.keys():
evalParams.update( p['p'] if isinstance(p['p'], dict) else json.loads(p['p'][1:-1]) )
validate_data_fn(p['g'], p['s'], evalParams)
print('SUCCESS')
sys.exit(0)
except Exception as e:
print(str(e))
sys.exit(101) |