def proc_netScale(self, im, cropSz, poseImSz, bodyPt):
#Crop the image at different scales
t = time.time()
imData = np.zeros((len(LIST_SCALES), cropSz, cropSz, 3))
scData = np.zeros((len(LIST_SCALES), 2))
posData = np.zeros((len(LIST_SCALES), 2))
for i,s in enumerate(LIST_SCALES):
imData[i], scs, crpPos = imu.centered_crop(cropSz, copy.deepcopy(im), bodyPt, s, returnScale=True)
scData[i] = np.array(scs).reshape(1,2)
posData[i] = np.array(crpPos).reshape(1,2)
print('crop time: {:.3f}s').format(time.time() - t)
#Use the scale net to find the best scale
t = time.time()
scaleOp = self.netScale_.forward(blobs=['fc-op'], data=imData)
print('netScale time: {:.3f}s').format(time.time() - t)
scaleIdx = scaleOp['fc-op'].squeeze().argmax()
scale = LIST_SCALES[scaleIdx]
#Scale to use to return the image in the original space
oScale = scData[scaleIdx]
#Original location of the cropped image
oPos = posData[scaleIdx]
#Prepare image for pose prediction
imScale = imData[scaleIdx]
print(scaleIdx)
print(len(imData))
xSt, ySt = (cropSz - poseImSz)/2, (cropSz - poseImSz)/2
xEn, yEn = xSt + poseImSz, ySt + poseImSz
imScale = imScale[ySt:yEn, xSt:xEn,:].reshape((1,poseImSz,poseImSz,3))
return imScale, xSt, ySt, oPos, oScale, scaleIdx
def proc_fixedScale(self, im, cropSz, poseImSz, bodyPt, scaleIdx):
imScale = np.zeros((cropSz, cropSz, 3))
oScale = np.zeros((2))
oPos = np.zeros((2))
scale = LIST_SCALES[scaleIdx]
imScale, scs, crpPos = imu.centered_crop(cropSz, copy.deepcopy(im), bodyPt, scale, returnScale=True)
oScale = np.array(scs).reshape(1,2)
oPos = np.array(crpPos).reshape(1,2)
xSt, ySt = (cropSz - poseImSz)/2, (cropSz - poseImSz)/2
xEn, yEn = xSt + poseImSz, ySt + poseImSz
imScale = imScale[ySt:yEn, xSt:xEn,:].reshape((1,poseImSz,poseImSz,3))
return imScale, xSt, ySt, oPos, oScale, scaleIdx
def predict(self,
imName='./test_images/mpii-test-079555750.jpg',
bodyPt=(249, 249),
returnIm=False):
'''
imName : image file name for which the pose needs to be predicted
bodyPt : A point on the body of the person (torso) for whom the pose
is to be predicted
returnIm: If True, return the image also
'''
cropSz, poseImSz = self.cropSz_, self.poseImSz_
#Read the image
if (isinstance(imName, str)):
im = scm.imread(imName)
else:
im = imName
#Crop the image at different scales
imData = np.zeros((len(LIST_SCALES), cropSz, cropSz, 3))
scData = np.zeros((len(LIST_SCALES), 2))
posData = np.zeros((len(LIST_SCALES), 2))
for i, s in enumerate(LIST_SCALES):
imData[i], scs, crpPos = imu.centered_crop(cropSz,
copy.deepcopy(im),
bodyPt,
s,
returnScale=True)
scData[i] = np.array(scs).reshape(1, 2)
posData[i] = np.array(crpPos).reshape(1, 2)
#Use the scale net to find the best scale
scaleOp = self.netScale_.forward(blobs=['fc-op'], data=imData)
scaleIdx = scaleOp['fc-op'].squeeze().argmax()
scale = LIST_SCALES[scaleIdx]
#Scale to use to return the image in the original space
oScale = scData[scaleIdx]
#Original location of the cropped image
oPos = posData[scaleIdx]
#Prepare image for pose prediction
imScale = imData[scaleIdx]
xSt, ySt = (cropSz - poseImSz) / 2, (cropSz - poseImSz) / 2
xEn, yEn = xSt + poseImSz, ySt + poseImSz
imScale = imScale[ySt:yEn, xSt:xEn, :].reshape(
(1, poseImSz, poseImSz, 3))
#Seed pose
currPose = np.zeros((1, 17, 2, 1)).astype(np.float32)
for i in range(16):
currPose[0, i, 0] = copy.deepcopy(self.seedPose_[0, i] - xSt)
currPose[0, i, 1] = copy.deepcopy(self.seedPose_[1, i] - ySt)
#The marking point is the center of the image
currPose[0, 16, 0] = poseImSz / 2
currPose[0, 16, 1] = poseImSz / 2
#Dummy labels
labels = np.zeros((1, 16, 2, 1)).astype(np.float32)
#Predict Pose
for step in range(4):
poseOp = self.netPose_.forward(blobs=['cls3_fc'],
image=imScale,
kp_pos=copy.deepcopy(currPose),
label=labels)
kPred = copy.deepcopy(poseOp['cls3_fc'].squeeze())
for i in range(16):
dx, dy = kPred[i], kPred[16 + i]
currPose[0, i, 0] = currPose[0, i, 0] + self.mxStepSz_ * dx
currPose[0, i, 1] = currPose[0, i, 1] + self.mxStepSz_ * dy
#Convert the pose in the original image coordinated
origPose = (currPose.squeeze() +
np.array([xSt, ySt]).reshape(1, 2)) * oScale + oPos
if returnIm:
#return origPose, copy.deepcopy(currPose), imScale[0]
return origPose, im
else:
return origPose, copy.deepcopy(currPose)
def predict(self, imName='./test_images/mpii-test-079555750.jpg',
bodyPt=(249,249), returnIm=False):
'''
imName : image file name for which the pose needs to be predicted
bodyPt : A point on the body of the person (torso) for whom the pose
is to be predicted
returnIm: If True, return the image also
'''
cropSz, poseImSz = self.cropSz_, self.poseImSz_
#Read the image
if(isinstance(imName, str)):
im = scm.imread(imName)
else:
im = imName
#Crop the image at different scales
imData = np.zeros((len(LIST_SCALES), cropSz, cropSz, 3))
scData = np.zeros((len(LIST_SCALES), 2))
posData = np.zeros((len(LIST_SCALES), 2))
for i,s in enumerate(LIST_SCALES):
imData[i], scs, crpPos = imu.centered_crop(cropSz, copy.deepcopy(im), bodyPt, s,
returnScale=True)
scData[i] = np.array(scs).reshape(1,2)
posData[i] = np.array(crpPos).reshape(1,2)
#Use the scale net to find the best scale
scaleOp = self.netScale_.forward(blobs=['fc-op'], data=imData)
scaleIdx = scaleOp['fc-op'].squeeze().argmax()
scale = LIST_SCALES[scaleIdx]
#Scale to use to return the image in the original space
oScale = scData[scaleIdx]
#Original location of the cropped image
oPos = posData[scaleIdx]
#Prepare image for pose prediction
imScale = imData[scaleIdx]
xSt, ySt = (cropSz - poseImSz)/2, (cropSz - poseImSz)/2
xEn, yEn = xSt + poseImSz, ySt + poseImSz
imScale = imScale[ySt:yEn, xSt:xEn,:].reshape((1,poseImSz,poseImSz,3))
#Seed pose
currPose = np.zeros((1,17,2,1)).astype(np.float32)
for i in range(16):
currPose[0,i,0] = copy.deepcopy(self.seedPose_[0,i] - xSt)
currPose[0,i,1] = copy.deepcopy(self.seedPose_[1,i] - ySt)
#The marking point is the center of the image
currPose[0, 16, 0] = poseImSz / 2
currPose[0, 16, 1] = poseImSz / 2
#Dummy labels
labels = np.zeros((1,16,2,1)).astype(np.float32)
#Predict Pose
for step in range(4):
poseOp = self.netPose_.forward(blobs=['cls3_fc'], image=imScale,
kp_pos=copy.deepcopy(currPose), label=labels)
kPred = copy.deepcopy(poseOp['cls3_fc'].squeeze())
for i in range(16):
dx, dy = kPred[i], kPred[16 + i]
currPose[0,i,0] = currPose[0,i,0] + self.mxStepSz_ * dx
currPose[0,i,1] = currPose[0,i,1] + self.mxStepSz_ * dy
#Convert the pose in the original image coordinated
origPose = (currPose.squeeze() + np.array([xSt, ySt]).reshape(1,2)) * oScale + oPos
if returnIm:
#return origPose, copy.deepcopy(currPose), imScale[0]
return origPose, im
else:
return origPose, copy.deepcopy(currPose)