def set():
# parse input arguments
parser = argparse.ArgumentParser()
parser.add_argument("type",metavar="TYPE",help="type of network",choices=["CNN","STN","cSTN","ICSTN"])
parser.add_argument("--group",default="0",help="name for group")
parser.add_argument("--model",default="test",help="name for model instance")
parser.add_argument("--recurN",type=int,default=4,help="number of recurrent transformations (for IC-STN)")
parser.add_argument("--lr",type=float,default=1e-2,help="learning rate for classification network")
parser.add_argument("--lrST",type=float,default=1e-4,help="learning rate for geometric predictor")
parser.add_argument("--batchSize",type=int,default=200,help="batch size for SGD")
parser.add_argument("--maxIter",type=int,default=100000,help="maximum number of training iterations")
parser.add_argument("--warpType",metavar="WARPTYPE",help="type of warp function on images",default="homography",
choices=["translation","similarity","affine","homography"])
parser.add_argument("--resume",type=int,default=0,help="resume from iteration number")
parser.add_argument("--gpu",type=int,default=0,help="ID of GPU device (if there are multiple)")
opt = parser.parse_args()
opt.warpScale = {"pert":0.25,"trans":0.25}
opt.baseLR,opt.baseLRST = opt.lr,opt.lrST
# --- below are automatically set ---
opt.H,opt.W = 28,28
opt.visBlockSize = 12
opt.GPUdevice = "/gpu:{0}".format(opt.gpu)
opt.pDim = 2 if opt.warpType == "translation" else \
4 if opt.warpType == "similarity" else \
6 if opt.warpType == "affine" else \
8 if opt.warpType == "homography" else None
opt.canon4pts = np.array([[-1,-1],[-1,1],[1,1],[1,-1]],dtype=np.float32)
opt.Im4pts = np.array([[0,0],[0,opt.H-1],[opt.W-1,opt.H-1],[opt.W-1,0]],dtype=np.float32)
opt.warpGTmtrx = warp.fit(opt.canon4pts,opt.Im4pts,"affine")
if opt.type=="CNN": opt.baseLRST = 0
return opt
def __init__(self, args):
self.warpScale = {"pert": 0.25, "trans": 0.25}
self.warpType = args.warpType
self.batchSize = args.batchSize
self.baseLR, self.baseLRST = args.lr, args.lrST
# --- below are automatically set ---
self.H, self.W = 28, 28
self.visBlockSize = 12
self.GPUdevice = "/gpu:{0}".format(args.gpu)
self.pDim = 2 if self.warpType == "translation" else \
4 if self.warpType == "similarity" else \
6 if self.warpType == "affine" else \
8 if self.warpType == "homography" else None
self.canon4pts = np.array([[-1, -1], [-1, 1], [1, 1], [1, -1]], dtype=np.float32)
self.Im4pts = np.array([[0, 0], [0, self.H - 1], [self.W - 1, self.H - 1], [self.W - 1, 0]], dtype=np.float32)
self.warpGTmtrx = warp.fit(self.canon4pts, self.Im4pts, "affine")
if args.type == "CNN": self.baseLRST = 0
def set(training):
# parse input arguments
parser = argparse.ArgumentParser()
parser.add_argument("netType",
choices=["CNN", "STN", "IC-STN"],
help="type of network")
parser.add_argument("--group", default="0", help="name for group")
parser.add_argument("--model",
default="test",
help="name for model instance")
parser.add_argument("--size", default="36x36", help="image resolution")
parser.add_argument("--sizeFull",
default="50x50",
help="full image resolution")
parser.add_argument(
"--warpType",
default="homography",
help="type of warp function on images",
choices=["translation", "similarity", "affine", "homography"])
parser.add_argument(
"--warpN",
type=int,
default=4,
help="number of recurrent transformations (for IC-STN)")
parser.add_argument("--stdC",
type=float,
default=0.01,
help="initialization stddev (classification network)")
parser.add_argument("--stdGP",
type=float,
default=0.001,
help="initialization stddev (geometric predictor)")
parser.add_argument("--pertScale",
type=float,
default=0.25,
help="initial perturbation scale")
parser.add_argument("--transScale",
type=float,
default=0.25,
help="initial translation scale")
if training: # training
parser.add_argument("--batchSize",
type=int,
default=100,
help="batch size for SGD")
parser.add_argument("--lrC",
type=float,
default=1e-2,
help="learning rate (classification network)")
parser.add_argument(
"--lrCdecay",
type=float,
default=0.1,
help="learning rate decay (classification network)")
parser.add_argument(
"--lrCstep",
type=int,
default=500000,
help="learning rate decay step size (classification network)")
parser.add_argument("--lrGP",
type=float,
default=None,
help="learning rate (geometric predictor)")
parser.add_argument("--lrGPdecay",
type=float,
default=0.1,
help="learning rate decay (geometric predictor)")
parser.add_argument(
"--lrGPstep",
type=int,
default=500000,
help="learning rate decay step size (geometric predictor)")
parser.add_argument("--fromIt",
type=int,
default=0,
help="resume training from iteration number")
parser.add_argument("--toIt",
type=int,
default=1000000,
help="run training to iteration number")
else: # evaluation
parser.add_argument("--batchSize",
type=int,
default=1,
help="batch size for evaluation")
opt = parser.parse_args()
if opt.lrGP is None: opt.lrGP = 0 if opt.netType=="CNN" else \
1e-3 if opt.netType=="STN" else \
3e-5 if opt.netType=="IC-STN" else None
# --- below are automatically set ---
opt.training = training
opt.H, opt.W = [int(x) for x in opt.size.split("x")]
opt.fullH, opt.fullW = [int(x) for x in opt.sizeFull.split("x")]
opt.visBlockSize = int(np.floor(np.sqrt(opt.batchSize)))
opt.warpDim = 2 if opt.warpType == "translation" else \
4 if opt.warpType == "similarity" else \
6 if opt.warpType == "affine" else \
8 if opt.warpType == "homography" else None
opt.labelN = 43
opt.canon4pts = np.array([[-1, -1], [-1, 1], [1, 1], [1, -1]],
dtype=np.float32)
opt.image4pts = np.array(
[[0, 0], [0, opt.H - 1], [opt.W - 1, opt.H - 1], [opt.W - 1, 0]],
dtype=np.float32)
opt.bbox = [
int(opt.fullW / 2 - opt.W / 2),
int(opt.fullH / 2 - opt.H / 2),
int(opt.fullW / 2 + opt.W / 2),
int(opt.fullH / 2 + opt.H / 2)
]
opt.bbox4pts = np.array(
[[opt.bbox[0], opt.bbox[1]], [opt.bbox[0], opt.bbox[3]],
[opt.bbox[2], opt.bbox[3]], [opt.bbox[2], opt.bbox[1]]],
dtype=np.float32)
opt.refMtrx = warp.fit(Xsrc=opt.canon4pts, Xdst=opt.image4pts)
opt.bboxRefMtrx = warp.fit(Xsrc=opt.canon4pts, Xdst=opt.bbox4pts)
if opt.netType == "STN": opt.warpN = 1
print("({0}) {1}".format(util.toGreen("{0}".format(opt.group)),
util.toGreen("{0}".format(opt.model))))
print("------------------------------------------")
print("network type: {0}, recurrent warps: {1}".format(
util.toYellow("{0}".format(opt.netType)),
util.toYellow(
"{0}".format(opt.warpN if opt.netType == "IC-STN" else "X"))))
print("batch size: {0}, image size: {1}x{2}".format(
util.toYellow("{0}".format(opt.batchSize)),
util.toYellow("{0}".format(opt.H)),
util.toYellow("{0}".format(opt.W))))
print("warpScale: (pert) {0} (trans) {1}".format(
util.toYellow("{0}".format(opt.pertScale)),
util.toYellow("{0}".format(opt.transScale))))
if training:
print("[geometric predictor] stddev={0}, lr={1}".format(
util.toYellow("{0:.0e}".format(opt.stdGP)),
util.toYellow("{0:.0e}".format(opt.lrGP))))
print("[classification network] stddev={0}, lr={1}".format(
util.toYellow("{0:.0e}".format(opt.stdC)),
util.toYellow("{0:.0e}".format(opt.lrC))))
print("------------------------------------------")
if training:
print(
util.toMagenta("training model ({0}) {1}...".format(
opt.group, opt.model)))
return opt
def set(training):
# parse input arguments
parser = argparse.ArgumentParser()
parser.add_argument("--group", default="0", help="name for group")
parser.add_argument("--name",
default="test",
help="name for model instance")
parser.add_argument("--loadGP",
default=None,
help="load pretrained model (GP)")
parser.add_argument("--gpu",
default="0",
help="ID of GPU device (if there are multiple)")
parser.add_argument("--size",
default="120x160",
help="resolution of background image")
parser.add_argument("--warpN",
type=int,
default=1,
help="number of spatial transformations")
parser.add_argument("--stdGP",
type=float,
default=0.01,
help="initialization stddev (GP)")
parser.add_argument("--stdD",
type=float,
default=0.01,
help="initialization stddev (D)")
if training: # training
parser.add_argument("--loadD",
default=None,
help="load pretrained model (D)")
parser.add_argument("--lrGP",
type=float,
default=1e-6,
help="base learning rate (GP)")
parser.add_argument("--lrGPdecay",
type=float,
default=1.0,
help="learning rate decay (GP)")
parser.add_argument("--lrGPstep",
type=int,
default=10000,
help="learning rate decay step size (GP)")
parser.add_argument("--lrD",
type=float,
default=1e-4,
help="base learning rate (D)")
parser.add_argument("--lrDdecay",
type=float,
default=1.0,
help="learning rate decay (D)")
parser.add_argument("--lrDstep",
type=int,
default=10000,
help="learning rate decay step size (D)")
parser.add_argument("--unpaired",
action="store_true",
help="feed unpaired samples to D")
parser.add_argument("--dplambda",
type=float,
default=0.3,
help="warp update norm penalty factor")
parser.add_argument("--gradlambda",
type=float,
default=10.0,
help="gradient penalty factor")
parser.add_argument("--updateD",
type=int,
default=2,
help="update N times (D)")
parser.add_argument("--updateGP",
type=int,
default=1,
help="update N times (GP)")
parser.add_argument("--batchSize",
type=int,
default=20,
help="batch size for SGD")
parser.add_argument("--fromIt",
type=int,
default=0,
help="resume training from iteration number")
parser.add_argument("--toIt",
type=int,
default=40000,
help="run training to iteration number")
parser.add_argument("--initPert",
type=float,
default=0.1,
help="scale of initial perturbation")
parser.add_argument("--homoPert",
type=float,
default=0.1,
help="scale of homography perturbation")
else: # evaluation
parser.add_argument("--batchSize",
type=int,
default=1,
help="batch size for evaluation")
parser.add_argument("--initPert",
type=float,
default=0.0,
help="scale of initial perturbation")
opt = parser.parse_args()
# ------ probably won't touch these ------
opt.warpType = "homography"
opt.warpDim = 8
opt.warpApprox = 20
opt.GPUdevice = "/gpu:0"
# ------ below automatically set ------
opt.training = training
opt.H, opt.W = [int(x) for x in opt.size.split("x")]
if training:
opt.visBlockSize = int(np.floor(np.sqrt(opt.batchSize)))
# opt.visBlockSize = 2
opt.canon4pts = np.array([[-1, -1], [-1, 1], [1, 1], [1, -1]],
dtype=np.float32)
opt.image4pts = np.array(
[[0, 0], [0, opt.H - 1], [opt.W - 1, opt.H - 1], [opt.W - 1, 0]],
dtype=np.float32)
opt.refMtrx = warp.fit(Xsrc=opt.canon4pts, Xdst=opt.image4pts)
print("({0}) {1}".format(util.toGreen("{0}".format(opt.group)),
util.toGreen("{0}".format(opt.name))))
print("------------------------------------------")
print("GPU device: {0}, batch size: {1}, warps: {2}".format(
util.toYellow("{0}".format(opt.gpu)),
util.toYellow("{0}".format(opt.batchSize)),
util.toYellow("{0}".format(opt.warpN))))
print("image size: {0}x{1}".format(util.toYellow("{0}".format(opt.H)),
util.toYellow("{0}".format(opt.W))))
if training:
print(
"[GP] stddev={3}, lr={0}, decay={1}, step={2}, update={4}".format(
util.toYellow("{0:.0e}".format(opt.lrGP)),
util.toYellow("{0}".format(opt.lrGPdecay)),
util.toYellow("{0}".format(opt.lrGPstep)),
util.toYellow("{0:.0e}".format(opt.stdGP)),
util.toYellow("{0}".format(opt.updateGP))))
print(
"[D] stddev={3}, lr={0}, decay={1}, step={2}, update={4}".format(
util.toYellow("{0:.0e}".format(opt.lrD)),
util.toYellow("{0}".format(opt.lrDdecay)),
util.toYellow("{0}".format(opt.lrDstep)),
util.toYellow("{0:.0e}".format(opt.stdD)),
util.toYellow("{0}".format(opt.updateD))))
print("------------------------------------------")
if training:
print(
util.toMagenta("training model ({0}) {1}...".format(
opt.group, opt.name)))
return opt
def set(training):
# parse input arguments
parser = argparse.ArgumentParser()
parser.add_argument("--group", default="0", help="name for group")
parser.add_argument("--name", default="test", help="name for model instance")
parser.add_argument("--loadGP", default=None, help="load pretrained model (GP)")
parser.add_argument("--size", default="128x128", help="resolution of foreground image")
parser.add_argument("--warpType", default="affine", help="type of warp function on foreground image")
parser.add_argument("--warpN", type=int, default=1, help="number of spatial transformations")
parser.add_argument("--stdGP", type=float, default=0.01, help="initialization stddev (GP)")
parser.add_argument("--stdD", type=float, default=0.01, help="initialization stddev (D)")
if training: # training
parser.add_argument("--loadD", default=None, help="load pretrained model (D)")
parser.add_argument("--lrGP", type=float, default=1e-5, help="base learning rate (GP)")
parser.add_argument("--lrGPdecay", type=float, default=1.0, help="learning rate decay (GP)")
parser.add_argument("--lrGPstep", type=int, default=20000, help="learning rate decay step size (GP)")
parser.add_argument("--lrD", type=float, default=1e-5, help="base learning rate (D)")
parser.add_argument("--lrDdecay", type=float, default=1.0, help="learning rate decay (D)")
parser.add_argument("--lrDstep", type=int, default=20000, help="learning rate decay step size (D)")
parser.add_argument("--dplambda", type=float, default=1.0, help="warp update norm penalty factor")
parser.add_argument("--gradlambda", type=float, default=10.0, help="gradient penalty factor")
parser.add_argument("--updateD", type=int, default=2, help="update N times (D)")
parser.add_argument("--updateGP", type=int, default=1, help="update N times (GP)")
parser.add_argument("--batchSize", type=int, default=20, help="batch size for SGD")
parser.add_argument("--histSize", type=float, default=10, help="history size in batch")
parser.add_argument("--histQsize", type=int, default=10000, help="history queue size for updating D")
parser.add_argument("--fromIt", type=int, default=0, help="resume training from iteration number")
parser.add_argument("--toIt", type=int, default=50000, help="run training to iteration number")
parser.add_argument("--pertFG", type=float, default=0.1, help="scale of initial perturbation (bags)")
parser.add_argument("--pertBG", type=float, default=0.1, help="scale of initial perturbation (face)")
else: # evaluation
parser.add_argument("--batchSize", type=int, default=10, help="batch size for evaluation")
parser.add_argument("--pertFG", type=float, default=0.0, help="scale of initial perturbation (bags)")
parser.add_argument("--pertBG", type=float, default=0.0, help="scale of initial perturbation (face)")
parser.add_argument("--loadImage", default=None, help="load image to test")
opt = parser.parse_args()
# ------ probably won't touch these ------
## for original network
# opt.dataH,opt.dataW = 144,144
# opt.centerY,opt.centerX = 72,72
## for our new network
opt.dataH,opt.dataW = 128,128
opt.centerY,opt.centerX = 64,64
opt.warpDim = 8 if opt.warpType=="homography" else \
6 if opt.warpType=="affine" else None
opt.warpApprox = 20
opt.GPUdevice = "/gpu:0"
# ------ below automatically set ------
opt.training = training
opt.H,opt.W = [int(x) for x in opt.size.split("x")]
if training:
opt.visBlockSize = int(np.floor(np.sqrt(opt.batchSize)))
opt.canon4pts = np.array([[-1,-1],[-1,1],[1,1],[1,-1]],dtype=np.float32)
opt.image4pts = np.array([[0,0],[0,opt.H-1],[opt.W-1,opt.H-1],[opt.W-1,0]],dtype=np.float32)
opt.refMtrx = warp.fit(Xsrc=opt.canon4pts,Xdst=opt.image4pts)
opt.image4pts_b = np.array([[opt.centerX-opt.W//2,opt.centerY-opt.H//2],
[opt.centerX-opt.W//2,opt.centerY+opt.H//2],
[opt.centerX+opt.W//2,opt.centerY+opt.H//2],
[opt.centerX+opt.W//2,opt.centerY-opt.H//2]],dtype=np.float32)
opt.refMtrx_b = warp.fit(Xsrc=opt.canon4pts,Xdst=opt.image4pts_b)
print("({0}) {1}".format(
util.toGreen("{0}".format(opt.group)),
util.toGreen("{0}".format(opt.name))))
print("------------------------------------------")
print("batch size: {0}, warps: {1}".format(
util.toYellow("{0}".format(opt.batchSize)),
util.toYellow("{0}".format(opt.warpN))))
print("image size: {0}x{1}".format(
util.toYellow("{0}".format(opt.H)),
util.toYellow("{0}".format(opt.W))))
if training:
print("[GP] stddev={3}, lr={0}, decay={1}, step={2}, update={4}".format(
util.toYellow("{0:.0e}".format(opt.lrGP)),
util.toYellow("{0}".format(opt.lrGPdecay)),
util.toYellow("{0}".format(opt.lrGPstep)),
util.toYellow("{0:.0e}".format(opt.stdGP)),
util.toYellow("{0}".format(opt.updateGP))))
print("[D] stddev={3}, lr={0}, decay={1}, step={2}, update={4}".format(
util.toYellow("{0:.0e}".format(opt.lrD)),
util.toYellow("{0}".format(opt.lrDdecay)),
util.toYellow("{0}".format(opt.lrDstep)),
util.toYellow("{0:.0e}".format(opt.stdD)),
util.toYellow("{0}".format(opt.updateD))))
print("------------------------------------------")
if training:
print(util.toMagenta("training model ({0}) {1}...".format(opt.group,opt.name)))
return opt
