def classifyLocalImagesWithDismantler(self, corpusPath = None):
Opt_dmtler = Option_Dismantler(isTrain = False)
Dmtler = Dismantler(Opt_dmtler)
if corpusPath is None:
corpusPath = self.Opt.classifyCorpusPath
if self.Classifier is not None:
print 'Start classifying images with dismantler in local disk...'
startTime = time.time()
nImageAll = 0
header = ['file_path', 'number_subimages', 'sub_class_name', 'sub_probability', 'segmentation', 'subimage_height', 'subimage_width']
csvSavingPath = self.Opt.resultPath
csvFilename = 'class_result'
Common.saveCSV(csvSavingPath, csvFilename, header = header, mode = 'wb', consoleOut = False)
for dirPath, dirNames, fileNames in os.walk(corpusPath):
for f in fileNames:
fname, suffix = Common.getFileNameAndSuffix(f)
if suffix in self.Opt.validImageFormat:
filename = os.path.join(dirPath, f)
# Load image
img = ImageLoader.loadImageByPath(filename)
# Dismantle image
nodeList = Dmtler.dismantle(img)
# Get number of sub-images
if len(nodeList) > 0:
numSubImages = len(nodeList)
else:
numSubImages = 1
# Remove surrounding empty space
nodeList = Dmtler.updateImageToEffectiveAreaFromNodeList(img, nodeList, Opt_dmtler.thresholds)
# Load all sub-images
if len(nodeList) > 0:
imData, imDims, dimSum = ImageLoader.loadSubImagesByNodeList(img, nodeList, self.Opt.finalDim, self.Opt.preserveAspectRatio)
else:
imData, imDims, dimSum = ImageLoader.loadImagesByList([filename], self.Opt.finalDim, self.Opt.preserveAspectRatio)
# Extracting Features
X = self.FeatureDescriptor.extractFeatures(imData, 1)
# Classify
y_pred, y_proba = self.Classifier.predict(X)
sub_classes = ''
sub_probs = ''
sub_height = ''
sub_width = ''
segmentations = ''
for i in range(0, len(nodeList)):
if i != 0:
sub_classes += ','
sub_probs += ','
sub_height += ','
sub_width += ','
segmentations += ','
sub_classes += str(y_pred[i])
sub_height += str(imDims[i][0])
sub_width += str(imDims[i][1])
sub_prob = ''
for j in range(0, len(y_proba[i])):
if j != 0:
sub_prob += ':'
sub_prob += str(y_proba[i][j])
sub_probs += sub_prob
node = nodeList[i]
segmentation = str(node.info['start'][0]) + ':' + \
str(node.info['start'][1]) + ':' + \
str(node.info['end'][0]) + ':' + \
str(node.info['end'][1])
segmentations += segmentation
result = zip([filename], [numSubImages], [sub_classes], [sub_probs], [segmentations], [sub_height], [sub_width])
print result
Common.saveCSV(csvSavingPath, csvFilename, result, mode = 'ab', consoleOut = False)
nImageAll += 1
if np.mod(nImageAll, 100) == 0:
print '%d images have been classified.' % nImageAll
costTime = time.time() - startTime
print 'All %d images were classified and saved in %s within %d sec.' % (nImageAll, os.path.join(csvSavingPath, csvFilename), costTime)
else:
print 'Classifier not loaded'
def classifyCloudImagesWithDismantler(self, keyPath = None, host = None):
Opt_dmtler = Option_Dismantler(isTrain = False)
Dmtler = Dismantler(Opt_dmtler)
if self.Classifier is not None:
try:
cImageLoader = CloudImageLoader(self.Opt, keyPath = keyPath, host = host)
bucketList = cImageLoader.getBucketList()
except:
print 'Unable to connect cloud server'
print 'Start classifying images on cloud server...'
startTime = time.time()
nImageAll = 0
header = ['file_path', 'number_subimages', 'sub_class_name', 'sub_probability', 'segmentation', 'subimage_height', 'subimage_width']
csvSavingPath = self.Opt.resultPath
csvFilename = 'class_result'
Common.saveCSV(csvSavingPath, csvFilename, header = header, mode = 'wb', consoleOut = False)
for key in bucketList:
isValidImage, suffix = cImageLoader.isKeyValidImageFormat(key)
if isValidImage:
# Get image from s3
img = CloudImageLoader.keyToValidImage(key)
# Dismantle the image
nodeList = Dmtler.dismantle(img)
# Get number of sub-images
if len(nodeList) > 0:
numSubImages = len(nodeList)
else:
numSubImages = 1
# Remove surrounding empty space
nodeList = Dmtler.updateImageToEffectiveAreaFromNodeList(img, nodeList, Opt_dmtler.thresholds)
# Load all sub-images
if len(nodeList) > 0:
imData, imDims, dimSum = ImageLoader.loadSubImagesByNodeList(img, nodeList, self.Opt.finalDim, self.Opt.preserveAspectRatio)
else:
imData, imDim = ImageLoader.preImageProcessing(img, self.Opt.finalDim, self.Opt.preserveAspectRatio)
# Extracting Features
X = self.FeatureDescriptor.extractFeatures(imData, 1)
# Classify
y_pred, y_proba = self.Classifier.predict(X)
sub_classes = ''
sub_probs = ''
sub_height = ''
sub_width = ''
segmentations = ''
for i in range(0, len(nodeList)):
if i != 0:
sub_classes += ','
sub_probs += ','
sub_height += ','
sub_width += ','
segmentations += ','
sub_classes += str(y_pred[i])
sub_height += str(imDims[i][0])
sub_width += str(imDims[i][1])
sub_prob = ''
for j in range(0, len(y_proba[i])):
if j != 0:
sub_prob += ':'
sub_prob += str(y_proba[i][j])
sub_probs += sub_prob
node = nodeList[i]
segmentation = str(node.info['start'][0]) + ':' + \
str(node.info['start'][1]) + ':' + \
str(node.info['end'][0]) + ':' + \
str(node.info['end'][1])
segmentations += segmentation
result = zip([key.name], [numSubImages], [sub_classes], [sub_probs], [segmentations], [sub_height], [sub_width])
Common.saveCSV(csvSavingPath, csvFilename, result, mode = 'ab', consoleOut = False)
nImageAll += 1
if np.mod(nImageAll, 100) == 0:
print '%d images have been classified' % nImageAll
costTime = time.time() - startTime
print 'All %d images were classified and saved in %s within %d sec.' % (nImageAll, os.path.join(csvSavingPath, csvFilename), costTime)
else:
print 'Classifier not loaded'
