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 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 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 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 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 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