def calImgHisFeatures(imgFile,
gridSize,
sizeRange,
imResize=None,
gridList=None,
norm=True,
HisFeaDim=64):
# print imgFile
if imResize:
gridPatchData, positions, im = esg.generateGridPatchData(
imgFile,
gridSize,
sizeRange,
imResize=imResize,
gridList=gridList,
imNorm=False)
else:
gridPatchData, positions, im = esg.generateGridPatchData(
imgFile, gridSize, sizeRange, gridList=gridList, imNorm=False)
feaVecs = np.zeros((len(gridPatchData), HisFeaDim))
for i in range(len(gridPatchData)):
feaVec, _ = histogramOfPatch(gridPatchData[i], HisFeaDim)
feaVecs[i, :] = feaVec
if norm:
feaVecs = nv.normalizeVecs(feaVecs)
return feaVecs, np.array(positions)
def intensityFeature(imgFile=None,
gridSize=None,
sizeRange=None,
gridPatchData=None,
imResize=None,
gridList=None,
diffResolution=True):
if gridPatchData is None:
if imResize:
gridPatchData, positions, im = esg.generateGridPatchData(
imgFile,
gridSize,
sizeRange,
imResize=imResize,
gridList=gridList)
else:
gridPatchData, positions, im = esg.generateGridPatchData(
imgFile,
gridSize,
sizeRange,
gridList=gridList,
diffResolution=diffResolution)
if not diffResolution:
gridPatchData_v = np.array(gridPatchData)
patch_num = len(gridPatchData)
mean_v = np.mean(np.mean(gridPatchData_v, axis=1), axis=1).reshape(
(patch_num, 1))
# i = 16
# patch_i = gridPatchData[i]
# mean_i = patch_i.mean()
shape = gridPatchData_v.shape
gridPatchData_reshape = gridPatchData_v.reshape(
(shape[0], shape[1] * shape[2]))
min_v = np.min(gridPatchData_reshape, axis=1).reshape((patch_num, 1))
max_v = np.max(gridPatchData_reshape, axis=1).reshape((patch_num, 1))
# min_i = patch_i.min()
# max_i = patch_i.max()
intensityFeas = np.hstack((min_v, mean_v, max_v))
else:
i = 0
patch_i = gridPatchData[i]
mean_i = patch_i.mean()
# print mean_i
feas_list = [[np.min(x), np.mean(x), np.max(x)] for x in gridPatchData]
intensityFeas = np.array(feas_list)
mean_i = intensityFeas[i, 1]
# print mean_i
# print min_v.shape
# print gridPatchData_v.shape
# print mean_i, mean_v[i], min_i, min_v[i], max_i, max_v[i]
# print intensityFeas.min(), intensityFeas.max()
return intensityFeas
def selectSpecialPatch(imgFile,
wordsFile,
feaType,
gridSize,
sizeRange,
nk,
filter_radius=3,
spaceSize=10):
feaVecs, posVecs = glf.genImgLocalFeas(imgFile, feaType, gridSize,
sizeRange)
# print feaVecs.shape, posVecs.shape
labelVecs = chm.calPatchLabels2(wordsFile,
feaVecs,
k=nk,
two_classes=['1', '2'],
isH1=True)
posVecs_f, labelVecs_f = filterPos(posVecs,
labelVecs,
radius=filter_radius,
spaceSize=spaceSize)
specialIDs = list(np.argwhere(labelVecs_f == 0)[:, 0])
specialPos = list(posVecs_f[specialIDs, :])
patchData, _, _ = esg.generateGridPatchData(imgFile,
gridSize,
sizeRange,
gridList=specialPos)
# patchData_arr = np.array(patchData)
return patchData, specialPos
def threshHoldFilterPatch(im, gridSize, sizeRange):
patchData, gridList, _ = esg.generateGridPatchData(im, gridSize, sizeRange)
patchData_arr = np.array(patchData)
mm = np.mean(np.mean(patchData_arr, axis=2), axis=1)
ths = mm - 26
ids = list(np.where(ths > 0))
print ids
gridList = [gridList[x] for x in ids[0]]
return gridList
def calImgSDAEFea(imgFile,
model,
gridSize,
sizeRange,
channels,
patch_mean,
gridList=None,
imResize=None,
patchMean=True,
norm=True):
patchSize = sizeRange[0]
if imResize:
gridPatchData, gridList, im = esg.generateGridPatchData(
imgFile, gridSize, sizeRange, imResize=imResize, gridList=gridList)
else:
gridPatchData, gridList, im = esg.generateGridPatchData(
imgFile, gridSize, sizeRange, gridList=gridList)
# gridPatchData, gridList, im = esg.generateGridPatchData(imgFile, gridSize, sizeRange, gridList=gridList)
patchData = [
p.reshape(channels, patchSize, patchSize) for p in gridPatchData
]
patchData = np.array(patchData) - patch_mean
if patchMean:
means = np.mean(np.mean(patchData, axis=-1), axis=-1)
means = means.reshape(means.shape[0], means.shape[1], 1, 1)
means = np.tile(means, (1, 1, patchSize, patchSize))
patchData -= means
labelData = np.full((len(gridList), ), int(0), dtype='float32')
model.set_input_arrays(patchData, labelData)
out = model.forward()
out_name = model.blobs.items()[-1][0]
feaVec = out[out_name]
posVec = np.array(gridList)
if norm:
feaVec = nv.normalizeVecs(feaVec)
return feaVec, posVec
def calImgDSift(imgFile,
gridSize,
sizeRange,
gridList=None,
imResize=None,
withIntensity=None,
diffResolution=True):
# print imgFile
siftFeaDim = 128
# if withIntensity:
# siftFeaDim += 3
if imResize:
patches, positions, im = esg.generateGridPatchData(
imgFile,
gridSize,
sizeRange,
imResize=imResize,
gridList=gridList,
diffResolution=diffResolution)
else:
patches, positions, im = esg.generateGridPatchData(
imgFile,
gridSize,
sizeRange,
gridList=gridList,
diffResolution=diffResolution)
feaVecs = np.zeros((len(patches), siftFeaDim))
for i in range(len(patches)):
patchSize = int(positions[i][-1])
extractor = dsift.SingleSiftExtractor(patchSize)
feaVec = extractor.process_image(patches[i])
feaVecs[i, :] = feaVec
if withIntensity is True:
intensityFeas = intensityFeature(gridPatchData=patches,
diffResolution=diffResolution)
feaVecs = np.hstack((feaVecs, intensityFeas))
return feaVecs, np.array(positions)
def saveImgHeatMaps(imgFile, isReduce=False):
sdae_wordsFile_h1 = '../../Data/Features/type4_SDAEWords_h1.hdf5'
sdae_wordsFile_h2 = '../../Data/Features/type4_SDAEWords_h2.hdf5'
sdae_wordsFile_h1_diff_mean = '../../Data/Features/type4_SDAEWords_h1_diff_mean.hdf5'
sdae_wordsFile_h2_diff_mean = '../../Data/Features/type4_SDAEWords_h2_diff_mean.hdf5'
sdae_wordsFile_h1_reduce = '../../Data/Features/type4_SDAEWords_h1_reduce_sameRatio.hdf5'
sdae_wordsFile_h2_reduce = '../../Data/Features/type4_SDAEWords_h2_reduce_sameRatio.hdf5'
sift_wordsFile_h1 = '../../Data/Features/type4_SIFTWords_h1.hdf5'
sift_wordsFile_h2 = '../../Data/Features/type4_SIFTWords_h2.hdf5'
sift_wordsFile_h1_reduce = '../../Data/Features/type4_SIFTWords_h1_reduce.hdf5'
sift_wordsFile_h2_reduce = '../../Data/Features/type4_SIFTWords_h2_reduce.hdf5'
lbp_wordsFile_h1_reduce = '../../Data/Features/type4_LBPWords_h1_reduce_sameRatio.hdf5'
lbp_wordsFile_h2_reduce = '../../Data/Features/type4_LBPWords_h2_reduce_sameRatio.hdf5'
lbp_wordsFile_h1 = '../../Data/Features/type4_LBPWords_h1.hdf5'
lbp_wordsFile_h2 = '../../Data/Features/type4_LBPWords_h2.hdf5'
SIFTFeaFile = '../../Data/Features/type4_SIFTFeatures.hdf5'
SDAEFeaFile = '../../Data/Features/type4_SDAEFeas.hdf5'
LBPFeaFile = '../../Data/Features/type4_LBPFeatures.hdf5'
sift_saveName_h1 = '../../Data/Features/type4_SIFTWords_h1_s16_600_300_300_300.hdf5'
sift_saveName_h2 = '../../Data/Features/type4_SIFTWords_h2_s16_600_300_300_300.hdf5'
sdae_saveName_h1 = '../../Data/Features/type4_SDAEWords_h1_diff_mean_s16_600_300_300_300.hdf5'
sdae_saveName_h2 = '../../Data/Features/type4_SDAEWords_h2_diff_mean_s16_600_300_300_300.hdf5'
sdae_saveName_h1_s = '../../Data/Features/type4_SDAEWords_h1_same_mean_s16_600_300_300_300.hdf5'
sdae_saveName_h2_s = '../../Data/Features/type4_SDAEWords_h2_same_mean_s16_600_300_300_300.hdf5'
lbp_saveName_h1 = '../../Data/Features/type4_LBPWords_h1_s16_600_300_300_300.hdf5'
lbp_saveName_h2 = '../../Data/Features/type4_LBPWords_h2_s16_600_300_300_300.hdf5'
sizeRange = (16, 16)
imResize = (256, 256)
imgSize = (440, 440)
nk = 19
resolution = 5
gridSize = np.array([resolution, resolution])
im = np.array(imread(imgFile), dtype='f') / 255
th1 = 0.5
th2 = 0.5
im_name = imgFile[-20:-4]
# ----------------save sift------------------
feaVectors, posVectors = glf.genImgLocalFeas(imgFile,
'SIFT',
gridSize,
sizeRange,
imResize=None)
if isReduce:
feaVectors = pca.reduceVecFeasDim(SIFTFeaFile, feaVectors, 64)
heats = generateHeatMaps2by2(sift_wordsFile_h1_reduce,
sift_wordsFile_h2_reduce, feaVectors,
posVectors, gridSize, nk, th1, th2)
else:
heats = generateHeatMaps2by2(sift_saveName_h1, sift_saveName_h2,
feaVectors, posVectors, gridSize, nk, th1,
th2)
for c, m in heats.iteritems():
map3 = np.transpose(m, (1, 0, 2)).reshape(440, 440 * 3)
map3 = np.append(map3, im, axis=1)
if isReduce:
imsave(im_name + '_SIFT_reduce_' + c + '_th' + str(th1) + '.jpg',
map3)
else:
imsave(im_name + '_SIFT_' + c + '_th' + str(th1) + '.jpg', map3)
# ----------------save lbp------------------
feaVectors, posVectors = glf.genImgLocalFeas(imgFile,
'LBP',
gridSize,
sizeRange,
imResize=None)
if isReduce:
feaVectors = pca.reduceVecFeasDim(LBPFeaFile, feaVectors, 8)
heats = generateHeatMaps2by2(lbp_wordsFile_h1_reduce,
lbp_wordsFile_h2_reduce, feaVectors,
posVectors, gridSize, nk, th1, th2)
else:
heats = generateHeatMaps2by2(lbp_saveName_h1, lbp_saveName_h2,
feaVectors, posVectors, gridSize, nk, th1,
th2)
for c, m in heats.iteritems():
map3 = np.transpose(m, (1, 0, 2)).reshape(440, 440 * 3)
map3 = np.append(map3, im, axis=1)
if isReduce:
imsave(im_name + '_LBP_reduce_' + c + '_th' + str(th1) + '.jpg',
map3)
else:
imsave(im_name + '_LBP_' + c + '_th' + str(th1) + '.jpg', map3)
# ---------------show SDEA local results--------------
# define SDAE parameters
sdaePara = {}
# sdaePara['weight'] = '../../Data/autoEncoder/final_0.01.caffemodel'
# sdaePara['weight'] = '../../Data/autoEncoder/layer_diff_mean_final.caffemodel'
sdaePara[
'weight'] = '../../Data/autoEncoder/layer_diff_mean_s16_final.caffemodel'
sdaePara['net'] = '../../Data/autoEncoder/test_net.prototxt'
sdaePara['meanFile'] = '../../Data/patchData_mean_s16.txt'
sdaePara['patchMean'] = True
channels = 1
# layerNeuronNum = [28 * 28, 2000, 1000, 500, 128]
layerNeuronNum = [16 * 16, 1000, 1000, 500, 64]
sdaePara['layerNeuronNum'] = layerNeuronNum
_, gl, _ = esg.generateGridPatchData(imgFile, gridSize, sizeRange)
batchSize = len(gl)
inputShape = (batchSize, channels, 16, 16)
sdaePara['inputShape'] = inputShape
feaVectors, posVectors = glf.genImgLocalFeas(imgFile,
'SDAE',
gridSize,
sizeRange,
sdaePara=sdaePara)
if isReduce:
feaVectors = pca.reduceVecFeasDim(SDAEFeaFile, feaVectors, 9)
heats = generateHeatMaps2by2(sdae_wordsFile_h1_reduce,
sdae_wordsFile_h2_reduce, feaVectors,
posVectors, gridSize, nk, th1, th2)
else:
heats = generateHeatMaps2by2(sdae_saveName_h1, sdae_saveName_h2,
feaVectors, posVectors, gridSize, nk, th1,
th2)
for c, m in heats.iteritems():
map3 = np.transpose(m, (1, 0, 2)).reshape(440, 440 * 3)
map3 = np.append(map3, im, axis=1)
if isReduce:
imsave(im_name + '_SDAE_reduce_' + c + '_th' + str(th1) + '.jpg',
map3)
else:
imsave(im_name + '_SDAE_' + c + '_th' + str(th1) + '.jpg', map3)
return 0
# # print feaVecs.shape, posVecs.shape
# labelVecs = chm.calPatchLabels2(w, feaVecs, k=nk, two_classes=['1', '2'], isH1=True)
# posVecs_f, labelVecs_f = filterPos(posVecs, labelVecs, radius=3, spaceSize=10)
# specialIDs = list(np.argwhere(labelVecs_f == 0)[:, 0])
# specialPos = list(posVecs_f[specialIDs, :])
wordsFile_s = [
lbp_wordsFile_s1, lbp_wordsFile_s2, lbp_wordsFile_s3, lbp_wordsFile_s4
]
specialType = 2
w = wordsFile_s[specialType]
patchData_a, specialPos = selectSpecialPatch(imgFile, w, feaType, gridSize,
sizeRange, nk)
# print labelVecs.shape
print len(specialPos)
print len(patchData_a)
im = imread(imgFile)
patchData, _, _ = esg.generateGridPatchData(im,
gridSize,
sizeRange,
gridList=specialPos)
print len(patchData)
pp = np.array(patchData)
background_mean = pp.mean()
print background_mean
mm = np.mean(np.mean(pp, axis=2), axis=1)
print mm.shape
plf.showGrid(im, specialPos)
plt.show()
specialList = threshHoldFilterPatch(im, gridSize, sizeRange)
plf.showGrid(im, specialList)
plt.show()
# ---------------show SDEA local results--------------
sdae_wordsFile_h1 = '../../Data/Features/SDAEWords_h1.hdf5'
sdae_wordsFile_h2 = '../../Data/Features/SDAEWords_h2.hdf5'
# define sdae model
weight = '../../Data/autoEncoder/final_0.01.caffemodel'
net = '../../Data/autoEncoder/test_net.prototxt'
meanFile = '../../Data/patchData_mean.txt'
f_mean = open(meanFile, 'r')
patch_mean = float(f_mean.readline().split(' ')[1])
f_mean.close()
channels = 1
layerNeuronNum = [28 * 28, 2000, 1000, 500, 128]
_, gl, _ = esg.generateGridPatchData(imgFile, gridSize, sizeRange)
batchSize = len(gl)
inputShape = (batchSize, channels, 28, 28)
with open(net, 'w') as f1:
f1.write(str(AE.defineTestNet(inputShape, layerNeuronNum)))
caffe.set_mode_gpu()
model = caffe.Net(net, weight, caffe.TEST)
feaVec, posVec = extSDAE.calImgSDAEFea(imgFile, model, gridSize, sizeRange, channels, patch_mean)
labelVectors_h = calPatchLabelHierarchy(sdae_wordsFile_h1, sdae_wordsFile_h2, feaVec)
showLocalLabel(imgFile, labelVectors_h, posVec, imResize=None, feaType='SDAE_')
filtered_pos, filtered_label = filterPos(posVec, labelVectors_h, 1, 10)
showLocalLabel(imgFile, filtered_label, filtered_pos, imResize=None, feaType='SDAE_filtered_')
gridSize = np.array([10, 10])
sizeRange = (28, 28)
patchSize = sizeRange[0]
channels = 1
posParaNum = 4
layerNeuronNum = [28 * 28, 1000, 1000, 500, 64]
SDAEFeaDim = layerNeuronNum[-1]
# weight = '../../Data/autoEncoder/final_0.01.caffemodel'
# weight = '../../Data/autoEncoder/layer_diff_mean_final.caffemodel'
# weight = '../../Data/autoEncoder/layer_same_mean_s16_final.caffemodel'
# weight = '../../Data/autoEncoder/layer_same_mean_s28_special_final.caffemodel'
weight = '../../Data/autoEncoder/layer_same_mean_s28_special_final.caffemodel'
net = '../../Data/autoEncoder/test_net.prototxt'
img_test = dataFolder + 'N20031221G030001.bmp'
gridPatchData, gridList, im = esg.generateGridPatchData(
img_test, gridSize, sizeRange)
batchSize = len(gridList)
inputShape = (batchSize, 1, 28, 28)
with open(net, 'w') as f1:
f1.write(str(AE.defineTestNet(inputShape, layerNeuronNum)))
caffe.set_mode_gpu()
model = caffe.Net(net, weight, caffe.TEST)
labelTruth = '../../Data/Alllabel2003_38044.txt'
# labelFile = '../../Data/type3_1000_500_500.txt'
# labelFile = '../../Data/type4_1500_500_500_500.txt'
# labelFile = '../../Data/type4_600_300_300_300.txt'
labelFile = '../../Data/type4_b500.txt'
print plf.compareLabeledFile(labelTruth, labelFile)
def makePatchData(labelFile,
patchSize,
gridSize=np.array([10, 10]),
imgType='.bmp',
channels=1,
savePath='../../Data/one_in_minute_patch_diff_mean.hdf5',
same_mean_file='../.../Data/patchData_mean_s16.txt',
imagesFolder='../../Data/labeled2003_38044/',
patchMean=True,
saveList='../../Data/patchList_diff_mean.txt',
subtract_same_mean=False):
sizeRange = (patchSize, patchSize)
[images, labels] = plf.parseNL(labelFile)
# arragedImages = plf.arrangeToClasses(images, labels, classNum)
f = h5py.File(savePath, 'w')
data = f.create_dataset('data', (0, channels, patchSize, patchSize),
dtype='f',
maxshape=(None, channels, patchSize, patchSize))
label = f.create_dataset('label', (0, ), dtype='i', maxshape=(None, ))
if subtract_same_mean:
patches_mean = 0
for i in range(len(images)):
imf = imagesFolder + images[i] + imgType
gridPatchData, gridList, _ = esg.generateGridPatchData(
imf, gridSize, sizeRange)
patchData = np.array(gridPatchData)
patches_mean += patchData.mean()
patch_mean = patches_mean / len(images)
print 'patch number: ' + str(data.shape[0])
print 'patch mean: ' + str(patch_mean)
with open(same_mean_file, 'w') as f2:
f2.write('patch_mean: ' + str(patch_mean))
f2.close()
else:
patch_mean = 0
print 'patch_mean: ', patch_mean
for i in range(len(images)):
imf = imagesFolder + images[i] + imgType
print imf
gridPatchData, gridList, _ = esg.generateGridPatchData(
imf, gridSize, sizeRange)
patchData = [
p.reshape(channels, patchSize, patchSize) for p in gridPatchData
]
patchData = np.array(patchData) - patch_mean
if patchMean:
means = np.mean(np.mean(patchData, axis=-1), axis=-1)
means = means.reshape(means.shape[0], means.shape[1], 1, 1)
means = np.tile(means, (1, 1, patchSize, patchSize))
patchData -= means
labelData = np.full((len(gridList), ), int(labels[i]), dtype='i')
oldNum = data.shape[0]
newNum = oldNum + patchData.shape[0]
data.resize(newNum, axis=0)
data[oldNum:newNum, :, :, :] = patchData
label.resize(newNum, axis=0)
label[oldNum:newNum, ] = labelData
f.close()
print 'make patch data done!'
with open(saveList, 'w') as f1:
f1.write(savePath)
f1.close()
print saveList + ' saved!'
return 0
def calImgLBPFeatures(imgFile,
gridSize,
sizeRange,
imResize=None,
gridList=None,
norm=True,
withIntensity=None,
diffResolution=False):
# print imgFile
P1 = 8
P2 = 16
P3 = 24
R1 = 1
R2 = 2
R3 = 3
if imResize:
gridPatchData, positions, im = esg.generateGridPatchData(
imgFile, gridSize, sizeRange, imResize=imResize, gridList=gridList)
else:
gridPatchData, positions, im = esg.generateGridPatchData(
imgFile, gridSize, sizeRange, gridList=gridList)
LBPFeaDim = 10 + 18 + 26
feaVecs = np.zeros((len(gridPatchData), LBPFeaDim))
for i in range(len(gridPatchData)):
LBP_img_R1P8 = feature.local_binary_pattern(gridPatchData[i],
P1,
R1,
method='uniform')
LBP_img_R2P16 = feature.local_binary_pattern(gridPatchData[i],
P2,
R2,
method='uniform')
LBP_img_R3P24 = feature.local_binary_pattern(gridPatchData[i],
P3,
R3,
method='uniform')
lbp_bin_num_R1P8 = P1 + 2
lbp_hist_R1P8, lbp_bins_R1P8 = np.histogram(
LBP_img_R1P8.flatten(), bins=range(lbp_bin_num_R1P8 + 1))
lbp_bin_num_R2P16 = P2 + 2
lbp_hist_R2P16, lbp_bins_R2P16 = np.histogram(
LBP_img_R2P16.flatten(), bins=range(lbp_bin_num_R2P16 + 1))
lbp_bin_num_R3P24 = P3 + 2
lbp_hist_R3P24, lbp_bins_R3P24 = np.histogram(
LBP_img_R3P24.flatten(), bins=range(lbp_bin_num_R3P24 + 1))
feaVec = np.array(
list(lbp_hist_R1P8) + list(lbp_hist_R2P16) + list(lbp_hist_R3P24))
feaVecs[i, :] = feaVec
if norm:
feaVecs = nv.normalizeVecs(feaVecs)
# print withIntensity
# print feaVecs.shape
if withIntensity is True:
intensityFeas = intensityFeature(gridPatchData=gridPatchData,
diffResolution=diffResolution)
feaVecs = np.hstack((feaVecs, intensityFeas))
return feaVecs, np.array(positions)
def calCascadeFeaSet(dataFolder,
labelFile,
siftFeaFile_reduce,
lbpFeaFile_reduce,
sdaeFeaFile_reduce_d,
sdaeFeaFile_reduce_s,
classNum,
imgType,
gridSize,
sizeRange,
classLabel,
sdaePara,
saveName,
saveFolder='../../Data/Features/'):
sift_f = h5py.File(siftFeaFile_reduce, 'r')
sdae_f_d = h5py.File(sdaeFeaFile_reduce_d, 'r')
sdae_f_s = h5py.File(sdaeFeaFile_reduce_s, 'r')
lbp_f = h5py.File(lbpFeaFile_reduce, 'r')
names, labels = plf.parseNL(labelFile)
if classNum == 4:
auroraData = plf.arrangeToClasses(names, labels, classNum, classLabel)
else:
auroraData, _ = plf.arrangeToClasses(names, labels, classNum,
classLabel)
f = h5py.File(saveFolder + saveName, 'w')
f.attrs['dataFolder'] = dataFolder
ad = f.create_group('auroraData')
for c, imgs in auroraData.iteritems():
ascii_imgs = [n.encode('ascii', 'ignore') for n in imgs]
ad.create_dataset(c, (len(ascii_imgs), ), 'S10', ascii_imgs)
feaSet = f.create_group('feaSet')
posSet = f.create_group('posSet')
for c, imgs in auroraData.iteritems():
# sift_u = np.array(sift_f.get('uSet/'+c))
# lbp_u = np.array(lbp_f.get('uSet/'+c))
# sdae_u_d = np.array(sdae_f_d.get('uSet/'+c))
# sdae_u_s = np.array(sdae_f_s.get('uSet/'+c))
sift_u = np.array(sift_f.get('uSet/u'))
lbp_u = np.array(lbp_f.get('uSet/u'))
sdae_u_d = np.array(sdae_f_d.get('uSet/u'))
sdae_u_s = np.array(sdae_f_s.get('uSet/u'))
imgFile = dataFolder + imgs[0] + imgType
_, gl, _ = esg.generateGridPatchData(imgFile, gridSize, sizeRange)
feaVec, posVec = extractCascadeFeatures(imgFile, sift_u, lbp_u,
sdae_u_d, sdae_u_s, gl,
gridSize, sizeRange, sdaePara)
feaArr = np.empty((0, feaVec.shape[1]))
posArr = np.empty((0, posVec.shape[1]))
for name in imgs:
imgFile = dataFolder + name + imgType
batchSize = len(gl)
inputShape = (batchSize, 1, sizeRange[0], sizeRange[0])
sdaePara['inputShape'] = inputShape
feaVec, posVec = extractCascadeFeatures(imgFile, sift_u, lbp_u,
sdae_u_d, sdae_u_s, gl,
gridSize, sizeRange,
sdaePara)
feaArr = np.append(feaArr, feaVec, axis=0)
posArr = np.append(posArr, posVec, axis=0)
feaSet.create_dataset(c, feaArr.shape, 'f', feaArr)
posSet.create_dataset(c, posArr.shape, 'i', posArr)
f.close()
print saveFolder + saveName + ' saved'
return 0