def block(idx,
inmaps,
outmaps,
sizeconv,
strideconv,
initscheme,
actInPlace,
sizepool=2,
stridepool=2,
addMaxpool=True):
assert len(inmaps) == len(outmaps) == len(sizeconv) == len(
strideconv) == len(idx), "lengths must be the same size"
seq = Sequential()
for i in range(len(inmaps)):
seq.append(
Conv2D(inmaps=inmaps[i],
outmaps=outmaps[i],
size=sizeconv[i],
pad=sizeconv[i] // 2,
stride=strideconv[i],
initscheme=initscheme,
dilation=1,
useBias=True,
name="conv%s" % idx[i]))
seq.append(Activation(leakyRelu, inplace=actInPlace, args=(0.01, )))
if addMaxpool:
seq.append(
MaxPool2D(size=sizepool,
stride=stridepool,
name="conv%s_pool" % idx[-1]))
return seq
def convBlock(inmaps,
outmaps,
size,
stride,
pad,
dropout,
initscheme,
dilation=1,
bnAct=True,
name=None):
block = Sequential()
if pad > 0:
block.append(Pad1D(pad, mode=PadMode.reflect))
block.append(
Conv1D(inmaps,
outmaps,
size=size,
stride=stride,
pad=0,
dilation=dilation,
useBias=True,
initscheme=initscheme,
name="%s_conv" % name))
if bnAct:
block.append(BatchNorm1D(outmaps, epsilon=0.001, name="%s_bn" % name))
block.append(Activation(clip, args=(0.0, 20.0)))
if dropout > 0.0:
block.append(Dropout(p=dropout))
return block
def convBN(inmaps,
outmaps,
size,
stride,
pad,
name,
actInplace,
bnInplace,
scheme,
typ="bn"):
block = Sequential()
if typ == "bn":
names = ["conv_%s" % name, "bn_%s" % name, "relu_%s" % name]
elif typ == "v3":
names = ["%s_conv2d" % name, "%s_batchnorm" % name, "%s_relu" % name]
else:
raise ValueError("Unrecognized convBN type")
block.append(
Conv2D(inmaps,
outmaps,
size,
stride,
pad,
useBias=False,
initscheme=scheme,
name=names[0]))
block.append(BatchNorm2D(outmaps, inplace=bnInplace, name=names[1]))
block.append(Activation(relu, inplace=actInplace, name=names[2]))
return block
def residBlock(inmaps, hmaps, stride, blockname, convShortcut, actInplace,
bnInplace, initscheme):
block = Sequential()
branch = Sequential()
branch.extend(
residMiniBlock(inmaps, hmaps, 1, stride, 0, blockname, "2a", True,
actInplace, bnInplace, initscheme))
branch.extend(
residMiniBlock(hmaps, hmaps, 3, 1, 1, blockname, "2b", True,
actInplace, bnInplace, initscheme))
branch.extend(
residMiniBlock(hmaps, 4 * hmaps, 1, 1, 0, blockname, "2c", False,
actInplace, bnInplace, initscheme))
shortcut = Sequential()
if convShortcut:
shortcut.extend(
residMiniBlock(inmaps, 4 * hmaps, 1, stride, 0, blockname, "1",
False, actInplace, bnInplace, initscheme))
else:
shortcut.append(Identity())
block.append(Replicate(2))
block.append(Parallel().append(branch).append(shortcut))
block.append(Add())
block.append(Activation(relu, inplace=actInplace))
return block
def residMiniBlock(inmaps, outmaps, size, stride, pad, blockname, mininame,
addAct, actInplace, bnInplace, initscheme):
block = Sequential()
block.append(
Conv2D(inmaps,
outmaps,
size,
stride=stride,
pad=pad,
useBias=False,
initscheme=initscheme,
name="res%s_branch%s" % (blockname, mininame)))
block.append(
BatchNorm2D(outmaps,
name="bn%s_branch%s" % (blockname, mininame),
inplace=bnInplace))
if addAct:
block.append(
Activation(relu,
inplace=actInplace,
name="res%s_branch%s_relu" % (blockname, mininame)))
return block
def buildSmallBranch(inplace=True, num=1):
branch = Sequential()
branch.append(
Conv2D(128,
128,
3,
pad=1,
initscheme="none",
name="conv5_1_CPM_L%d" % num))
branch.append(
Activation(relu, inplace=inplace, name="relu5_1_CPM_L%d" % num))
branch.append(
Conv2D(128,
128,
3,
pad=1,
initscheme="none",
name="conv5_2_CPM_L%d" % num))
branch.append(
Activation(relu, inplace=inplace, name="relu5_2_CPM_L%d" % num))
branch.append(
Conv2D(128,
128,
3,
pad=1,
initscheme="none",
name="conv5_3_CPM_L%d" % num))
branch.append(
Activation(relu, inplace=inplace, name="relu5_3_CPM_L%d" % num))
branch.append(
Conv2D(128, 512, 1, initscheme="none", name="conv5_4_CPM_L%d" % num))
branch.append(
Activation(relu, inplace=inplace, name="relu5_4_CPM_L%d" % num))
branch.append(
Conv2D(512,
19 * (3 - num),
1,
initscheme="none",
name="conv5_5_CPM_L%d" % num))
return branch
def clipTest(): batchsize, maps, height, width = 4, 3, 5, 8 mod = Activation(clip, name="clip") data = gpuarray.to_gpu(np.random.randn(batchsize, maps, height, width).astype(np.float32)) engine = buildRTEngine(mod, data.shape, savepath="../TestData", dtype=DataType.float32) outdata = mod(data) enginedata = engine(data) assert np.allclose(outdata.get(), enginedata.get())
def trainSimpleTest(optCls, dtype, *args, **kwargs):
from PuzzleLib.Containers.Sequential import Sequential
from PuzzleLib.Modules.Linear import Linear
from PuzzleLib.Modules.Activation import Activation, relu
from PuzzleLib.Modules.Cast import Cast
from PuzzleLib.Cost.MSE import MSE
seq = Sequential()
seq.append(Linear(128, 64, useBias=False))
seq.append(Activation(relu))
seq.append(Linear(64, 32, useBias=False))
seq.append(Activation(relu))
seq.append(Linear(32, 16))
seq.calcMode(dtype)
seq.append(Cast(intype=dtype, outtype=np.float32))
optimizer = optCls(*args, **kwargs)
optimizer.setupOn(seq, useGlobalState=True)
mse = MSE()
data = gpuarray.to_gpu(np.random.randn(16, 128).astype(dtype))
target = gpuarray.to_gpu(np.random.randn(16, 16).astype(np.float32))
for i in range(200):
error, grad = mse(seq(data), target)
optimizer.zeroGradParams()
seq.backward(grad)
optimizer.update()
if (i + 1) % 5 == 0:
print("Iteration #%d error: %s" % (i + 1, error))
def rnnTest(): batchsize, inmaps, inh, inw = 4, 2, 3, 3 outmaps, hsize = 4, 1 seq = Sequential(name="rnn") seq.append(Conv2D(inmaps, outmaps, 3, pad=1)) seq.append(Activation(relu)) seq.append(Reshape(shape=(batchsize, outmaps, inh * inw))) seq.append(SwapAxes(0, 1)) seq.append(RNN(inh * inw, hsize, layers=2, direction="bi", mode="tanh", getSequences=True, hintBatchSize=batchsize)) seq.append(SwapAxes(0, 1)) data = gpuarray.to_gpu(np.random.randn(batchsize, inmaps, inh, inw).astype(np.float32)) engine = buildRTEngine(seq, data.shape, savepath="../TestData", dtype=DataType.float32) outdata = seq(data) enginedata = engine(data) assert np.allclose(outdata.get(), enginedata.get())
def trainHardTest(optCls, dtype, *args, **kwargs):
from PuzzleLib.Containers.Sequential import Sequential
from PuzzleLib.Modules.Conv2D import Conv2D
from PuzzleLib.Modules.BatchNorm2D import BatchNorm2D
from PuzzleLib.Modules.Activation import Activation, relu
from PuzzleLib.Modules.Cast import Cast
from PuzzleLib.Cost.MSE import MSE
seq = Sequential()
seq.append(Conv2D(4, 8, 5, pad=1))
seq.append(BatchNorm2D(8))
seq.append(Activation(relu))
seq.append(Conv2D(8, 16, 5, pad=1))
seq.calcMode(dtype)
seq.append(Cast(intype=dtype, outtype=np.float32))
optimizer = optCls(*args, **kwargs)
optimizer.setupOn(seq, useGlobalState=True)
mse = MSE()
data = gpuarray.to_gpu(np.random.randn(4, 4, 5, 5).astype(dtype))
target = gpuarray.to_gpu(np.random.randn(4, 16, 1, 1).astype(np.float32))
for i in range(200):
error, grad = mse(seq(data), target)
optimizer.zeroGradParams()
seq.backward(grad)
optimizer.update()
if (i + 1) % 5 == 0:
print("Iteration #%d error: %s" % (i + 1, error))
def loadNet(name="", inplace=True, modelpath=None):
net = Sequential(name)
net.append(Conv2D(3, 64, 3, pad=1, initscheme="none", name="conv1_1"))
net.append(Activation(relu, name="relu1_1", inplace=inplace))
net.append(Conv2D(64, 64, 3, pad=1, initscheme="none", name="conv1_2"))
net.append(Activation(relu, name="relu1_2", inplace=inplace))
net.append(MaxPool2D(name="pool1_stage1"))
net.append(Conv2D(64, 128, 3, pad=1, initscheme="none", name="conv2_1"))
net.append(Activation(relu, name="relu2_1", inplace=inplace))
net.append(Conv2D(128, 128, 3, pad=1, initscheme="none", name="conv2_2"))
net.append(Activation(relu, name="relu2_2", inplace=inplace))
net.append(MaxPool2D(name="pool2_stage1"))
net.append(Conv2D(128, 256, 3, pad=1, initscheme="none", name="conv3_1"))
net.append(Activation(relu, name="relu3_1", inplace=inplace))
net.append(Conv2D(256, 256, 3, pad=1, initscheme="none", name="conv3_2"))
net.append(Activation(relu, name="relu3_2", inplace=inplace))
net.append(Conv2D(256, 256, 3, pad=1, initscheme="none", name="conv3_3"))
net.append(Activation(relu, name="relu3_3", inplace=inplace))
net.append(Conv2D(256, 256, 3, pad=1, initscheme="none", name="conv3_4"))
net.append(Activation(relu, name="relu3_4", inplace=inplace))
net.append(MaxPool2D(name="pool3_stage1"))
net.append(Conv2D(256, 512, 3, pad=1, initscheme="none", name="conv4_1"))
net.append(Activation(relu, name="relu4_1", inplace=inplace))
net.append(Conv2D(512, 512, 3, pad=1, initscheme="none", name="conv4_2"))
net.append(Activation(relu, name="relu4_2", inplace=inplace))
net.append(
Conv2D(512, 256, 3, pad=1, initscheme="none", name="conv4_3_CPM"))
net.append(Activation(relu, name="relu4_3_CPM"))
net.append(
Conv2D(256, 128, 3, pad=1, initscheme="none", name="conv4_4_CPM"))
net.append(Activation(relu, name="relu4_4_CPM"))
block2 = buildSmallBlock(inplace=inplace)
block3 = buildBigBlock(stage=2, prenet=block2, inplace=inplace)
block4 = buildBigBlock(stage=3, prenet=block3, inplace=inplace)
block5 = buildBigBlock(stage=4, prenet=block4, inplace=inplace)
block6 = buildBigBlock(stage=5, prenet=block5, inplace=inplace)
net.extend(block6)
net.append(Replicate(2))
net.append(Parallel().append(buildBranch(stage=6, num=2,
inplace=inplace)).append(
buildBranch(stage=6,
num=1,
inplace=inplace)))
net.append(Concat(axis=1))
if modelpath is not None:
net.load(modelpath, assumeUniqueNames=True)
return net
def loadNiNImageNet(modelpath, poolmode="max", actInplace=False, initscheme="none", name="CaffeNet"):
if poolmode == "avg":
pool = AvgPool2D
elif poolmode == "max":
pool = MaxPool2D
else:
raise ValueError("Unsupported pool mode")
net = Sequential(name=name)
net.append(Conv2D(3, 96, 11, stride=4, initscheme=initscheme, name="conv1"))
net.append(Activation(relu, inplace=actInplace, name="relu0"))
net.append(Conv2D(96, 96, 1, stride=1, initscheme=initscheme, name="cccp1"))
net.append(Activation(relu, inplace=actInplace, name="relu1"))
net.append(Conv2D(96, 96, 1, stride=1, initscheme=initscheme, name="cccp2"))
net.append(Activation(relu, inplace=actInplace, name="relu2"))
net.append(pool(3, 2, name="pool1"))
net.append(Conv2D(96, 256, 5, stride=1, pad=2, initscheme=initscheme, name="conv2"))
net.append(Activation(relu, inplace=actInplace, name="relu3"))
net.append(Conv2D(256, 256, 1, stride=1, initscheme=initscheme, name="cccp3"))
net.append(Activation(relu, inplace=actInplace, name="relu4"))
net.append(Conv2D(256, 256, 1, stride=1, initscheme=initscheme, name="cccp4"))
net.append(Activation(relu, inplace=actInplace, name="relu5"))
net.append(pool(3, 2, name="pool2"))
net.append(Conv2D(256, 384, 3, stride=1, pad=1, initscheme=initscheme, name="conv3"))
net.append(Activation(relu, inplace=actInplace, name="relu6"))
net.append(Conv2D(384, 384, 1, stride=1, initscheme=initscheme, name="cccp5"))
net.append(Activation(relu, inplace=actInplace, name="relu7"))
net.append(Conv2D(384, 384, 1, stride=1, initscheme=initscheme, name="cccp6"))
net.append(Activation(relu, inplace=actInplace, name="relu8"))
net.append(pool(3, 2, name="pool3"))
net.append(Conv2D(384, 1024, 3, stride=1, pad=1, initscheme=initscheme, name="conv4-1024"))
net.append(Activation(relu, inplace=actInplace, name="relu9"))
net.append(Conv2D(1024, 1024, 1, stride=1, initscheme=initscheme, name="cccp7-1024"))
net.append(Activation(relu, inplace=actInplace, name="relu10"))
net.append(Conv2D(1024, 1000, 1, stride=1, initscheme=initscheme, name="cccp8-1024"))
net.append(Activation(relu, inplace=actInplace, name="relu11"))
net.append(AvgPool2D(5, 1, name="pool4"))
net.append(Flatten())
net.append(SoftMax())
if modelpath is not None:
net.load(modelpath)
return net
def loadInceptionBN(modelpath,
actInplace=False,
bnInplace=False,
initscheme="none",
name="Inception-BN-0126"):
net = Sequential(name=name)
net.append(
Conv2D(3,
64,
7,
stride=2,
pad=3,
useBias=False,
initscheme=initscheme,
name="conv_1"))
net.append(BatchNorm2D(64, inplace=bnInplace, name="bn_1"))
net.append(Activation(relu, inplace=actInplace, name="relu_1"))
net.append(MaxPool2D(3, 2, pad=1, name="pool_1"))
net.append(
Conv2D(64,
64,
1,
useBias=False,
initscheme=initscheme,
name="conv_2_red"))
net.append(BatchNorm2D(64, inplace=bnInplace, name="bn_2_red"))
net.append(Activation(relu, inplace=actInplace, name="relu_2_red"))
net.append(
Conv2D(64,
192,
3,
pad=1,
useBias=False,
initscheme=initscheme,
name="conv_2"))
net.append(BatchNorm2D(192, inplace=bnInplace, name="bn_2"))
net.append(Activation(relu, inplace=actInplace, name="relu_2"))
net.append(MaxPool2D(3, 2, pad=1, name="pool_2"))
act, bn = actInplace, bnInplace
net.extend(
bnBlock(192, [64], [64, 64], [64, 96, 96], [32],
act=act,
bn=bn,
scheme=initscheme,
name="3a"))
net.extend(
bnBlock(256, [64], [64, 96], [64, 96, 96], [64],
act=act,
bn=bn,
scheme=initscheme,
name="3b"))
net.extend(
bnShrinkBlock(320, [128, 160], [64, 96, 96],
bn=bn,
act=act,
scheme=initscheme,
name="3c"))
net.extend(
bnBlock(576, [224], [64, 96], [96, 128, 128], [128],
act=act,
bn=bn,
scheme=initscheme,
name="4a"))
net.extend(
bnBlock(576, [192], [96, 128], [96, 128, 128], [128],
act=act,
bn=bn,
scheme=initscheme,
name="4b"))
net.extend(
bnBlock(576, [160], [128, 160], [128, 160, 160], [128],
act=act,
bn=bn,
scheme=initscheme,
name="4c"))
net.extend(
bnBlock(608, [96], [128, 192], [160, 192, 192], [128],
act=act,
bn=bn,
scheme=initscheme,
name="4d"))
net.extend(
bnShrinkBlock(608, [128, 192], [192, 256, 256],
act=act,
bn=bn,
scheme=initscheme,
name="4e"))
net.extend(
bnBlock(1056, [352], [192, 320], [160, 224, 224], [128],
act=act,
bn=bn,
scheme=initscheme,
name="5a"))
net.extend(
bnBlock(1024, [352], [192, 320], [192, 224, 224], [128],
act=act,
bn=bn,
scheme=initscheme,
name="5b"))
net.append(AvgPool2D(7, 1, name="global_pool"))
net.append(Flatten(name="flatten"))
net.append(Linear(1024, 1000, initscheme=initscheme, name="fc1"))
net.append(SoftMax(name="softmax"))
if modelpath is not None:
net.load(modelpath, assumeUniqueNames=True)
return net
def buildBranch(inmaps=185, inplace=True, num=1, stage=2):
branch = Sequential()
branch.append(
Conv2D(inmaps,
128,
7,
pad=3,
initscheme="none",
name="Mconv1_stage%d_L%d" % (stage, num)))
branch.append(
Activation(relu,
inplace=inplace,
name="Mrelu1_stage%d_L%d" % (stage, num)))
branch.append(
Conv2D(128,
128,
7,
pad=3,
initscheme="none",
name="Mconv2_stage%d_L%d" % (stage, num)))
branch.append(
Activation(relu,
inplace=inplace,
name="Mrelu2_stage%d_L%d" % (stage, num)))
branch.append(
Conv2D(128,
128,
7,
pad=3,
initscheme="none",
name="Mconv3_stage%d_L%d" % (stage, num)))
branch.append(
Activation(relu,
inplace=inplace,
name="Mrelu3_stage%d_L%d" % (stage, num)))
branch.append(
Conv2D(128,
128,
7,
pad=3,
initscheme="none",
name="Mconv4_stage%d_L%d" % (stage, num)))
branch.append(
Activation(relu,
inplace=inplace,
name="Mrelu4_stage%d_L%d" % (stage, num)))
branch.append(
Conv2D(128,
128,
7,
pad=3,
initscheme="none",
name="Mconv5_stage%d_L%d" % (stage, num)))
branch.append(
Activation(relu,
inplace=inplace,
name="Mrelu5_stage%d_L%d" % (stage, num)))
branch.append(
Conv2D(128,
128,
1,
initscheme="none",
name="Mconv6_stage%d_L%d" % (stage, num)))
branch.append(
Activation(relu,
inplace=inplace,
name="Mrelu6_stage%d_L%d" % (stage, num)))
branch.append(
Conv2D(128,
19 * (3 - num),
1,
initscheme="none",
name="Mconv7_stage%d_L%d" % (stage, num)))
return branch
def loadInceptionV3(modelpath,
actInplace=False,
bnInplace=False,
initscheme="none",
name="Inception-7-0001"):
net = Sequential(name=name)
net.append(
Conv2D(3,
32,
3,
stride=2,
useBias=False,
initscheme=initscheme,
name="conv_conv2d"))
net.append(BatchNorm2D(32, name="conv_batchnorm"))
net.append(Activation(relu, inplace=actInplace, name="conv_relu"))
net.append(
Conv2D(32,
32,
3,
useBias=False,
initscheme=initscheme,
name="conv_1_conv2d"))
net.append(BatchNorm2D(32, name="conv_1_batchnorm"))
net.append(Activation(relu, inplace=actInplace, name="conv_1_relu"))
net.append(
Conv2D(32,
64,
3,
pad=1,
useBias=False,
initscheme=initscheme,
name="conv_2_conv2d"))
net.append(BatchNorm2D(64, name="conv_2_batchnorm"))
net.append(Activation(relu, inplace=actInplace, name="conv_2_relu"))
net.append(MaxPool2D(3, 2, name="pool"))
net.append(
Conv2D(64,
80,
1,
useBias=False,
initscheme=initscheme,
name="conv_3_conv2d"))
net.append(BatchNorm2D(80, name="conv_3_batchnorm"))
net.append(Activation(relu, inplace=actInplace, name="conv_3_relu"))
net.append(
Conv2D(80,
192,
3,
useBias=False,
initscheme=initscheme,
name="conv_4_conv2d"))
net.append(BatchNorm2D(192, name="conv_4_batchnorm"))
net.append(Activation(relu, inplace=actInplace, name="conv_4_relu"))
net.append(MaxPool2D(3, 2, name="pool1"))
act, bn = actInplace, bnInplace
net.extend(
bnBlock(192, [64], [48, 64], [64, 96, 96], [32], "mixed", act, bn,
initscheme, 5, 2, "v3"))
net.extend(
bnBlock(256, [64], [48, 64], [64, 96, 96], [64], "mixed_1", act, bn,
initscheme, 5, 2, "v3"))
net.extend(
bnBlock(288, [64], [48, 64], [64, 96, 96], [64], "mixed_2", act, bn,
initscheme, 5, 2, "v3"))
net.extend(
bnShrinkBlock(288, [384], [64, 96, 96], "mixed_3", act, bn, initscheme,
False, 0, "v3"))
net.extend(
factorBlock(768, [192], [128, 128, 192], [128, 128, 128, 128, 192],
[192], "mixed_4", act, bn, initscheme))
net.extend(
factorBlock(768, [192], [160, 160, 192], [160, 160, 160, 160, 192],
[192], "mixed_5", act, bn, initscheme))
net.extend(
factorBlock(768, [192], [160, 160, 192], [160, 160, 160, 160, 192],
[192], "mixed_6", act, bn, initscheme))
net.extend(
factorBlock(768, [192], [192, 192, 192], [192, 192, 192, 192, 192],
[192], "mixed_7", act, bn, initscheme))
net.extend(
v3ShrinkBlock(768, [192, 320], [192, 192, 192, 192], "mixed_8", act,
bn, initscheme))
net.extend(
expandBlock(1280, [320], [384, 384, 384], [448, 384, 384, 384], [192],
"mixed_9",
act,
bn,
initscheme,
pool="avg"))
net.extend(
expandBlock(2048, [320], [384, 384, 384], [448, 384, 384, 384], [192],
"mixed_10",
act,
bn,
initscheme,
pool="max"))
net.append(AvgPool2D(8, 1, name="global_pool"))
net.append(Flatten(name="flatten"))
net.append(Linear(2048, 1008, name="fc1"))
net.append(SoftMax(name="softmax"))
if modelpath is not None:
net.load(modelpath, assumeUniqueNames=True)
return net
def loadMiniYolo(modelpath, numOutput, actInplace=False, initscheme="none"):
net = Sequential(name="YOLONet")
block0 = block(idx=["1"],
inmaps=[3],
outmaps=[64],
sizeconv=[7],
strideconv=[2],
initscheme=initscheme,
actInPlace=actInplace)
net.extend(block0)
block1 = block(idx=["2"],
inmaps=[64],
outmaps=[192],
sizeconv=[3],
strideconv=[1],
initscheme=initscheme,
actInPlace=actInplace)
net.extend(block1)
block2 = block(idx=["3", "4", "5", "6"],
inmaps=[192, 128, 256, 256],
outmaps=[128, 256, 256, 512],
sizeconv=[1, 3, 1, 3],
strideconv=[1, 1, 1, 1],
initscheme=initscheme,
actInPlace=actInplace)
net.extend(block2)
block3 = block(
idx=["7", "8", "9", "10", "11", "12", "13", "14", "15", "16"],
inmaps=[512, 256, 512, 256, 512, 256, 512, 256, 512, 512],
outmaps=[256, 512, 256, 512, 256, 512, 256, 512, 512, 1024],
sizeconv=[1, 3, 1, 3, 1, 3, 1, 3, 1, 3],
strideconv=[1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
initscheme=initscheme,
actInPlace=actInplace)
net.extend(block3)
block4 = block(idx=["17", "18", "19", "20", "21", "22", "23", "24"],
inmaps=[1024, 512, 1024, 512, 1024, 1024, 1024, 1024],
outmaps=[512, 1024, 512, 1024, 1024, 1024, 1024, 1024],
sizeconv=[1, 3, 1, 3, 3, 3, 3, 3],
strideconv=[1, 1, 1, 1, 1, 2, 1, 1],
initscheme=initscheme,
actInPlace=actInplace,
addMaxpool=False)
net.extend(block4)
net.append(Flatten())
insize = int(np.prod(net.dataShapeFrom((1, 3, 448, 448))))
net.append(Linear(insize, 512, initscheme=initscheme, name="fc25"))
net.append(Activation(relu, inplace=actInplace, name="fc_relu24"))
net.append(Linear(512, 4096, initscheme=initscheme, name="fc26"))
net.append(Activation(relu, inplace=actInplace, name="fc_relu25"))
net.append(Linear(4096, numOutput, initscheme=initscheme, name="fc27"))
net.append(SoftMax())
if modelpath is not None:
net.load(modelpath)
return net
def loadVGG(modelpath, layers, poolmode="max", initscheme="none", withLinear=True, actInplace=False, name=None):
if poolmode == "avg":
pool = AvgPool2D
elif poolmode == "max":
pool = MaxPool2D
else:
raise ValueError("Unsupported pool mode")
if layers not in {"11", "16", "19"}:
raise ValueError("Unsupported VGG layers mode")
if name is None and layers == "11":
name = "VGG_ILSVRC_11_layers"
elif name is None and layers == "16":
name = "VGG_ILSVRC_16_layers"
elif name is None and layers == "19":
name = "VGG_ILSVRC_19_layers"
layers = int(layers)
net = Sequential(name=name)
net.append(Conv2D(3, 64, 3, pad=1, initscheme=initscheme, name="conv1_1"))
net.append(Activation(relu, inplace=actInplace, name="relu1_1"))
if layers > 11:
net.append(Conv2D(64, 64, 3, pad=1, initscheme=initscheme, name="conv1_2"))
net.append(Activation(relu, inplace=actInplace, name="relu1_2"))
net.append(pool(2, 2, name="pool1"))
net.append(Conv2D(64, 128, 3, pad=1, initscheme=initscheme, name="conv2_1"))
net.append(Activation(relu, inplace=actInplace, name="relu2_1"))
if layers > 11:
net.append(Conv2D(128, 128, 3, pad=1, initscheme=initscheme, name="conv2_2"))
net.append(Activation(relu, inplace=actInplace, name="relu2_2"))
net.append(pool(2, 2, name="pool2"))
net.append(Conv2D(128, 256, 3, pad=1, initscheme=initscheme, name="conv3_1"))
net.append(Activation(relu, inplace=actInplace, name="relu3_1"))
net.append(Conv2D(256, 256, 3, pad=1, initscheme=initscheme, name="conv3_2"))
net.append(Activation(relu, inplace=actInplace, name="relu3_2"))
if layers > 11:
net.append(Conv2D(256, 256, 3, pad=1, initscheme=initscheme, name="conv3_3"))
net.append(Activation(relu, inplace=actInplace, name="relu3_3"))
if layers > 16:
net.append(Conv2D(256, 256, 3, pad=1, initscheme=initscheme, name="conv3_4"))
net.append(Activation(relu, inplace=actInplace, name="relu3_4"))
net.append(pool(2, 2, name="pool3"))
net.append(Conv2D(256, 512, 3, pad=1, initscheme=initscheme, name="conv4_1"))
net.append(Activation(relu, inplace=actInplace, name="relu4_1"))
net.append(Conv2D(512, 512, 3, pad=1, initscheme=initscheme, name="conv4_2"))
net.append(Activation(relu, inplace=actInplace, name="relu4_2"))
if layers > 11:
net.append(Conv2D(512, 512, 3, pad=1, initscheme=initscheme, name="conv4_3"))
net.append(Activation(relu, inplace=actInplace, name="relu4_3"))
if layers > 16:
net.append(Conv2D(512, 512, 3, pad=1, initscheme=initscheme, name="conv4_4"))
net.append(Activation(relu, inplace=actInplace, name="relu4_4"))
net.append(pool(2, 2, name="pool4"))
net.append(Conv2D(512, 512, 3, pad=1, initscheme=initscheme, name="conv5_1"))
net.append(Activation(relu, inplace=actInplace, name="relu5_1"))
net.append(Conv2D(512, 512, 3, pad=1, initscheme=initscheme, name="conv5_2"))
net.append(Activation(relu, inplace=actInplace, name="relu5_2"))
if layers > 11:
net.append(Conv2D(512, 512, 3, pad=1, initscheme=initscheme, name="conv5_3"))
net.append(Activation(relu, inplace=actInplace, name="relu5_3"))
if layers > 16:
net.append(Conv2D(512, 512, 3, pad=1, initscheme=initscheme, name="conv5_4"))
net.append(Activation(relu, inplace=actInplace, name="relu5_4"))
net.append(pool(2, 2, name="pool5"))
if withLinear:
net.append(Flatten())
insize = int(np.prod(net.dataShapeFrom((1, 3, 224, 224))))
net.append(Linear(insize, 4096, initscheme=initscheme, name="fc6"))
net.append(Activation(relu, inplace=actInplace, name="relu6"))
net.append(Linear(4096, 4096, initscheme=initscheme, name="fc7"))
net.append(Activation(relu, inplace=actInplace, name="relu7"))
net.append(Linear(4096, 1000, initscheme=initscheme, name="fc8"))
net.append(SoftMax())
if modelpath is not None:
net.load(modelpath)
return net
def loadResNet(modelpath,
layers,
actInplace=False,
bnInplace=False,
initscheme="none",
name=None):
if layers == "50":
if name is None:
name = "ResNet-50"
level3names = ["3%s" % alpha for alpha in string.ascii_lowercase[1:4]]
level4names = ["4%s" % alpha for alpha in string.ascii_lowercase[1:6]]
elif layers == "101":
if name is None:
name = "ResNet-101"
level3names = ["3b%s" % num for num in range(1, 4)]
level4names = ["4b%s" % num for num in range(1, 23)]
elif layers == "152":
if name is None:
name = "ResNet-152"
level3names = ["3b%s" % num for num in range(1, 8)]
level4names = ["4b%s" % num for num in range(1, 36)]
else:
raise ValueError("Unsupported ResNet layers mode")
net = Sequential(name=name)
net.append(
Conv2D(3,
64,
7,
stride=2,
pad=3,
name="conv1",
initscheme=initscheme,
useBias=False))
net.append(BatchNorm2D(64, name="bn_conv1", inplace=bnInplace))
net.append(Activation(relu, inplace=actInplace, name="conv1_relu"))
net.append(MaxPool2D(3, 2, name="pool1"))
net.extend(
residBlock(64, 64, 1, "2a", True, actInplace, bnInplace, initscheme))
net.extend(
residBlock(256, 64, 1, "2b", False, actInplace, bnInplace, initscheme))
net.extend(
residBlock(256, 64, 1, "2c", False, actInplace, bnInplace, initscheme))
net.extend(
residBlock(256, 128, 2, "3a", True, actInplace, bnInplace, initscheme))
for name in level3names:
net.extend(
residBlock(512, 128, 1, name, False, actInplace, bnInplace,
initscheme))
net.extend(
residBlock(512, 256, 2, "4a", True, actInplace, bnInplace, initscheme))
for name in level4names:
net.extend(
residBlock(1024, 256, 1, name, False, actInplace, bnInplace,
initscheme))
net.extend(
residBlock(1024, 512, 2, "5a", True, actInplace, bnInplace,
initscheme))
net.extend(
residBlock(2048, 512, 1, "5b", False, actInplace, bnInplace,
initscheme))
net.extend(
residBlock(2048, 512, 1, "5c", False, actInplace, bnInplace,
initscheme))
net.append(AvgPool2D(7, 1))
net.append(Flatten())
net.append(Linear(2048, 1000, initscheme=initscheme, name="fc1000"))
net.append(SoftMax())
if modelpath is not None:
net.load(modelpath, assumeUniqueNames=True)
return net
def buildNet(vocabulary,
branches,
w2v,
sentlength,
embsize,
wscale,
dim=2,
branchMaps=100,
name="sentinet"):
def onVocabulary(W):
W[0] = np.zeros((1, embsize), dtype=np.float32)
arrayPOS = [
"", "_S", "_A", "_V", "_UNKN", "_ADJ", "_ADV", "_INTJ", "_NOUN",
"_PROPN", "_VERB", "_ADP", "_AUX", "_CCONJ", "_DET", "_NUM",
"_PART", "_PRON", "_SCONJ", "_SUM", "_X"
]
tmpPOS = []
if not w2v:
return
for word in vocabulary:
for pos in tmpPOS:
if (word + pos) in w2v.vocab:
W[vocabulary[word]] = w2v[word + pos]
break
for i, pos in enumerate(arrayPOS):
if (word + pos) in w2v.vocab:
tmpPOS.append(pos)
W[vocabulary[word]] = w2v[word + pos]
del arrayPOS[i]
break
net = Sequential(name)
net.setAttr("timestamp", int(time.time()))
net.append(
Embedder(vocabulary,
sentlength,
embsize,
wscale=wscale,
onVocabulary=onVocabulary,
learnable=True,
name="embedder"))
net.append(Reshape((-1, 1, sentlength, embsize)))
branchNum = len(branches)
net.append(Replicate(times=branchNum))
par = Parallel()
for branchFilterSize in branches:
par.append(
buildBranch(branchFilterSize, sentlength, branchMaps, embsize))
net.append(par)
net.append(Concat(axis=1))
net.append(Activation(relu))
net.append(Dropout(p=0.5))
net.append(Linear(branchNum * branchMaps, dim))
return net