def __getitem__(self, index):
img = self.LoadImage(index)
pts, c, s = self.GetPartInfo(index)
r = 0
if self.split == 'train':
s = s * (2 ** Rnd(ref.scale))
r = 0 if np.random.random() < 0.6 else Rnd(ref.rotate)
inp = Crop(img, c, s, r, ref.inputRes) / 256.
out = np.zeros((ref.nJoints, ref.outputRes, ref.outputRes))
Reg = np.zeros((ref.nJoints, 3))
for i in range(ref.nJoints):
if pts[i][0] > 1:
pt = Transform(pts[i], c, s, r, ref.outputRes)
out[i] = DrawGaussian(out[i], pt, ref.hmGauss)
Reg[i, :2] = pt
Reg[i, 2] = 1
if self.split == 'train':
if np.random.random() < 0.5:
inp = Flip(inp)
out = ShuffleLR(Flip(out))
Reg[:, 1] = Reg[:, 1] * -1
Reg = ShuffleLR(Reg)
#print 'before', inp[0].max(), inp[0].mean()
inp[0] = np.clip(inp[0] * (np.random.random() * (0.4) + 0.6), 0, 1)
inp[1] = np.clip(inp[1] * (np.random.random() * (0.4) + 0.6), 0, 1)
inp[2] = np.clip(inp[2] * (np.random.random() * (0.4) + 0.6), 0, 1)
#print 'after', inp[0].max(), inp[0].mean()
inp = torch.from_numpy(inp)
if self.returnMeta:
return inp, out, Reg, np.zeros((ref.nJoints, 3))
else:
return inp, out
def __getitem__(self, index):
img = self.LoadImage(index)
pts, c, s = self.GetPartInfo(index)
r = 0
if self.split == 'train':
s = s * (2**Rnd(ref.scale))
r = 0 if np.random.random() < 0.6 else Rnd(ref.rotate)
inp = Crop(img, c, s, r, ref.inputRes) / 256.
out = np.zeros((ref.nJoints, ref.outputRes, ref.outputRes))
for i in range(ref.nJoints):
if pts[i][0] > 1:
pt = Transform(pts[i], c, s, r, ref.outputRes)
out[i] = DrawGaussian(out[i], pt, ref.hmGauss)
if self.split == 'train':
if np.random.random() < 0.5:
inp = Flip(inp)
out = ShuffleLR(Flip(out))
inp[0] = np.clip(inp[0] * (np.random.random() * (0.4) + 0.6), 0, 1)
inp[1] = np.clip(inp[1] * (np.random.random() * (0.4) + 0.6), 0, 1)
inp[2] = np.clip(inp[2] * (np.random.random() * (0.4) + 0.6), 0, 1)
meta = np.zeros(1)
else:
meta = {'index': index, 'center': c, 'scale': s, 'rotate': r}
return inp, out, meta
def __getitem__(self, index):
img = self.LoadImage(index)
pts, action, c, s = self.GetPartInfo(index)
nb_pts = len(pts)
r = 0
flip = False
if self.split == 'train':
s = s * (2**Rnd(ref.scale))
r = 0 if np.random.random() < 0.6 else Rnd(ref.rotate)
inp = old_div(Crop(img, c, s, r, ref.inputRes), 256.)
if self.split == 'train':
if np.random.random() < 0.5:
inp = Flip(inp)
flip = True
inp[0] = np.clip(inp[0] * (np.random.random() * (0.4) + 0.6), 0, 1)
inp[1] = np.clip(inp[1] * (np.random.random() * (0.4) + 0.6), 0, 1)
inp[2] = np.clip(inp[2] * (np.random.random() * (0.4) + 0.6), 0, 1)
meta = np.zeros(1)
else:
meta = {'index': index, 'center': c, 'scale': s, 'rotate': r}
output = []
for k in range(nb_pts):
out = np.zeros((ref.nJoints, ref.outputRes, ref.outputRes))
for i in range(ref.nJoints):
if pts[k][i][0] > 1:
pt = Transform(pts[k][i], c, s, r, ref.outputRes)
out[i] = DrawGaussian(out[i], pt, ref.hmGauss)
if self.split == 'train':
out = ShuffleLR(Flip(out))
output.append(out)
return inp, output, action, meta
def __getitem__(self, index):
img = self.LoadImage(index)
pts2d, pts3d, emb, c, s = self.GetPartInfo(index)
s = min(s, max(img.shape[0], img.shape[1])) * 1.0
pts3d[:, 2] += s / 2
r = 0
if self.split == 'train':
s = s * (2**Rnd(ref.scale))
c[1] = c[1] + Rnd(ref.shiftY)
r = 0 if np.random.random() < 0.6 else Rnd(ref.rotate)
inp = Crop(img, c, s, r, ref.inputRes)
inp = inp.transpose(2, 0, 1).astype(np.float32) / 256.
starMap = np.zeros((1, ref.outputRes, ref.outputRes))
embMap = np.zeros((3, ref.outputRes, ref.outputRes))
depMap = np.zeros((1, ref.outputRes, ref.outputRes))
mask = np.concatenate([
np.ones((1, ref.outputRes, ref.outputRes)),
np.zeros((4, ref.outputRes, ref.outputRes))
])
for i in range(pts3d.shape[0]):
if self.annot['valid'][index][i] > ref.eps:
if (self.annot['vis'][index][i] > ref.eps):
pt3d = Transform3D(pts3d[i], c, s, r,
ref.outputRes).astype(np.int32)
pt2d = Transform(pts2d[i], c, s, r,
ref.outputRes).astype(np.int32)
if pt2d[0] >= 0 and pt2d[0] < ref.outputRes and pt2d[
1] >= 0 and pt2d[1] < ref.outputRes:
embMap[:, pt2d[1], pt2d[0]] = emb[i]
depMap[0, pt2d[1],
pt2d[0]] = 1.0 * pt3d[2] / ref.outputRes - 0.5
mask[1:, pt2d[1], pt2d[0]] = 1
starMap[0] = np.maximum(
starMap[0],
DrawGaussian(np.zeros((ref.outputRes, ref.outputRes)),
pt2d, ref.hmGauss).copy())
out = starMap
if 'emb' in self.opt.task:
out = np.concatenate([out, embMap])
if 'dep' in self.opt.task:
out = np.concatenate([out, depMap])
mask = mask[:out.shape[0]].copy()
if self.split == 'train':
if np.random.random() < 0.5:
inp = Flip(inp)
out = Flip(out)
mask = Flip(mask)
if 'emb' in self.opt.task:
out[1] = -out[1]
return inp, out, mask
def __getitem__(self, index):
if self.split == 'train':
index = np.random.randint(self.nVideos)
whichFrames, frameWiseData = self.annotations[index]
numFrames = len(whichFrames)
if self.loadConsecutive:
startpt = random.randint(1, numFrames - (self.nFramesLoad - 1))
inpFrames = np.zeros((3, self.nFramesLoad, 256, 256))
outPts_2ds = np.zeros((ref.nJoints, self.nFramesLoad, 2))
outOutRegs = np.ones((ref.nJoints, self.nFramesLoad, 1))
outPts_3d_monos = -1 * np.ones((ref.nJoints, self.nFramesLoad, 3))
outOutMaps = np.zeros(
(ref.nJoints, self.nFramesLoad, ref.outputRes, ref.outputRes))
meta = {}
nPersons = len(frameWiseData[whichFrames[startpt]])
if nPersons < 1:
return self.__getitem__(index + 1)
personIndex = random.randint(0, nPersons - 1)
meta['personIndex'] = personIndex
scale = 1
angle = 0
flipOrNot = 0
if self.split == 'train':
angle = 0 if np.random.random() < 0.5 else Rnd(ref.rotate)
scale = (2**Rnd(ref.scale))
flipOrNot = random.random() > 0.5
meta['s'] = scale
meta['r'] = angle
meta['flip'] = flipOrNot
for i in range(self.nFramesLoad):
a, b, c, d = self.getitem(startpt + i, meta, whichFrames,
frameWiseData)
inpFrames[:, i, :, :] = a
outOutMaps[:, i, :, :] = b
return (inpFrames, outOutMaps, outPts_2ds, outOutRegs,
outPts_3d_monos)
def __getitem__(self, index):
img = self.LoadImage(index)
class_id = self.annot['class_id'][index]
c, s, v = self.GetPartInfo(index)
s = min(s, max(img.shape[0], img.shape[1])) * 1.0
r = 0
if self.split == 'train':
s = s * (2 ** Rnd(ref.scale))
c[1] = c[1] + Rnd(ref.shiftY)
r = 0 if np.random.random() < 0.6 else Rnd(ref.rotate)
v[2] += r / 180.
v[2] += 2 if v[2] < -1 else (-2 if v[2] > 1 else 0)
inp = Crop(img, c, s, r, ref.inputRes)
inp = inp.transpose(2, 0, 1).astype(np.float32) / 256.
if self.split == 'train':
if np.random.random() < 0.5:
inp = Flip(inp)
v[0] = - v[0]
v[2] = - v[2]
v[2] += 2 if v[2] <= -1 else 0
#https://github.com/shubhtuls/ViewpointsAndKeypoints/blob/master/rcnnVp/rcnnBinnedJointTrainValTestCreate.m#L77
vv = v.copy()
if vv[0] < 0:
v[0] = self.opt.numBins - 1 - np.floor(-vv[0] * self.opt.numBins / 2.)
else:
v[0] = np.floor(vv[0] * self.opt.numBins / 2.)
v[1] = np.ceil(vv[1] * self.opt.numBins / 2. + self.opt.numBins / 2. - 1)
v[2] = np.ceil(vv[2] * self.opt.numBins / 2. + self.opt.numBins / 2. - 1)
v = v.astype(np.int32)
if self.opt.specificView:
vv = np.ones(3 * len(ref.pascalClassId), dtype = np.int32) * self.opt.numBins
vv[class_id * 3: class_id * 3 + 3] = v.copy()
v = vv.copy()
return inp, v