def mknet():
return df.Sequential( # 48x70 (HxW)
df.SpatialConvolution(3, 24, (3, 3)), # 46x68
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 24, (3, 3)), # 44x66
df.BatchNormalization(24),
df.SpatialMaxPooling((2, 3)), # 22x22
df.ReLU(),
df.SpatialConvolution(24, 48, (3, 3)), # 20x20
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 48, (3, 3)), # 18x18
df.BatchNormalization(48),
df.SpatialMaxPooling((2, 2)), # 9x9
df.ReLU(),
df.SpatialConvolution(48, 64, (3, 3)), # 7x7
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 3)), # 5x5
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64 * 5 * 5, 512),
df.ReLU(),
df.Dropout(0.5),
df.Linear(512, 2, init=df.init.normal(0.01)),
Biternion())
def mknet_gpu(*outlayers):
return df.Sequential( # 3@46
df.SpatialConvolutionCUDNN(3, 24, 3, 3), # -> 24@44
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolutionCUDNN(24, 24, 3, 3), # -> 24@42
df.BatchNormalization(24),
df.SpatialMaxPoolingCUDNN(2, 2), # -> 24@21
df.ReLU(),
df.SpatialConvolutionCUDNN(24, 48, 3, 3), # -> 48@19
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolutionCUDNN(48, 48, 3, 3), # -> 48@17
df.BatchNormalization(48),
df.SpatialMaxPooling(2, 2), # -> 48@9
df.ReLU(),
df.SpatialConvolutionCUDNN(48, 64, 3, 3), # -> 48@7
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolutionCUDNN(64, 64, 3, 3), # -> 48@5
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64 * 5 * 5, 512),
df.ReLU(),
df.Dropout(0.5),
*outlayers)
def __init__(self, weightsname, *unused, **unused_kw):
self._net = df.Sequential( # 48x70 (HxW)
df.SpatialConvolution(3, 24, (3, 3)), # 46x68
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 24, (3, 3)), # 44x66
df.BatchNormalization(24),
df.SpatialMaxPooling((2, 3)), # 22x22
df.ReLU(),
df.SpatialConvolution(24, 48, (3, 3)), # 20x20
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 48, (3, 3)), # 18x18
df.BatchNormalization(48),
df.SpatialMaxPooling((2, 2)), # 9x9
df.ReLU(),
df.SpatialConvolution(48, 64, (3, 3)), # 7x7
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 3)), # 5x5
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64 * 5 * 5, 512),
df.ReLU(),
df.Dropout(0.5),
df.Linear(512, 2, init=df.init.normal(0.01)),
Biternion())
self._net.__setstate__(np.load(weightsname))
self._net.evaluate()
self._aug = AugmentationPipeline(None, None, Cropper((48, 70)))
def mknet():
return df.Sequential( # 3@46
df.SpatialConvolution(3, 24, (3, 3)), # -> 24@44
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 24, (3, 3)), # -> 24@42
df.BatchNormalization(24),
df.SpatialMaxPooling((2, 2), ignore_border=False), # -> 24@21
df.ReLU(),
df.SpatialConvolution(24, 48, (3, 3)), # -> 48@19
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 48, (3, 3)), # -> 48@17
df.BatchNormalization(48),
df.SpatialMaxPooling((2, 2), ignore_border=False), # -> 48@9
df.ReLU(),
df.SpatialConvolution(48, 64, (3, 3)), # -> 64@7
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 3)), # -> 64@5
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64 * 5 * 5, 512),
df.ReLU(),
df.Dropout(0.5),
df.Linear(512, 2, init=df.init.normal(0.01)),
Biternion())
def mknet():
return df.Sequential( # 184x76
df.SpatialConvolution(3, 24, (3, 3)), # 182x74
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 24, (3, 3)), # 180x72
df.SpatialMaxPooling((3, 3)), # 60x24
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 48, (3, 3)), # 58x22
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 48, (3, 3)), # 56x20
df.SpatialMaxPooling((2, 2)), # 28x10
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 64, (3, 3)), # 26x8
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 3)), # 24x6
df.SpatialMaxPooling((2, 2)), # 12x3
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 2)), # 10x2
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64 * 10 * 2, 512),
df.ReLU(),
df.Dropout(0.5),
df.Linear(512, 2, init=df.init.normal(0.01)),
Biternion())
def __init__(self, weightsname, *unused, **unused_kw):
self._net = df.Sequential( # 3@46
df.SpatialConvolution( 3, 24, (3, 3)), # -> 24@44
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 24, (3, 3)), # -> 24@42
df.BatchNormalization(24),
df.SpatialMaxPooling((2, 2), ignore_border=False), # -> 24@21
df.ReLU(),
df.SpatialConvolution(24, 48, (3, 3)), # -> 48@19
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 48, (3, 3)), # -> 48@17
df.BatchNormalization(48),
df.SpatialMaxPooling((2, 2), ignore_border=False), # -> 48@9
df.ReLU(),
df.SpatialConvolution(48, 64, (3, 3)), # -> 64@7
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 3)), # -> 64@5
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64*5*5, 512),
df.ReLU(),
df.Dropout(0.5),
df.Linear(512, 2, init=df.init.normal(0.01)),
Biternion()
)
self._net.__setstate__(np.load(weightsname))
self._net.evaluate()
self._aug = AugmentationPipeline(None, None, Cropper((46, 46)))
def net():
model = df.Sequential()
model.add(df.Linear(28 * 28, 100))
model.add(df.ReLU())
model.add(df.Linear(100, 100))
model.add(df.ReLU())
model.add(df.Linear(100, 100))
model.add(df.ReLU())
model.add(df.Linear(100, 10))
model.add(df.SoftMax())
return model
def model(fully_conv=True):
conv3 = lambda nin, nout: df.SpatialConvolutionCUDNN(
nin, nout, 3, 3, border='same')
return df.Sequential(conv3(3, 64), df.ReLU(), conv3(64, 64), df.ReLU(),
df.SpatialMaxPoolingCUDNN(2, 2), conv3(64, 128),
df.ReLU(), conv3(128, 128), df.ReLU(),
df.SpatialMaxPoolingCUDNN(2, 2), conv3(128, 256),
df.ReLU(), conv3(256,
256), df.ReLU(), conv3(256, 256),
df.ReLU(), df.SpatialMaxPoolingCUDNN(2, 2),
conv3(256, 512), df.ReLU(), conv3(512,
512), df.ReLU(),
conv3(512, 512), df.ReLU(),
df.SpatialMaxPoolingCUDNN(2, 2), conv3(512, 512),
df.ReLU(), conv3(512, 512), df.ReLU(),
conv3(512, 512), df.ReLU(),
df.SpatialMaxPoolingCUDNN(2, 2),
*_vgg.model_head(fully_conv))
def lenet():
model = df.Sequential()
model.add(df.Reshape(-1, 1, 28, 28))
model.add(df.SpatialConvolution(1, 32, 5, 5, 1, 1, with_bias=False))
model.add(df.BatchNormalization(32))
model.add(df.ReLU())
model.add(df.SpatialMaxPooling(2, 2))
model.add(df.SpatialConvolution(32, 64, 5, 5, 1, 1, with_bias=False))
model.add(df.BatchNormalization(64))
model.add(df.ReLU())
model.add(df.SpatialMaxPooling(2, 2))
model.add(df.Reshape(-1, 4 * 4 * 64))
model.add(df.Linear(4 * 4 * 64, 100, with_bias=False))
model.add(df.BatchNormalization(100))
model.add(df.ReLU())
model.add(df.Dropout(0.5))
model.add(df.Linear(100, 10))
model.add(df.SoftMax())
return model
def lenet_cudnn():
model = df.Sequential()
model.add(df.Reshape(-1, 1, 28, 28))
model.add(
df.SpatialConvolutionCUDNN(1,
32,
5,
5,
1,
1,
border='same',
with_bias=False))
model.add(df.BatchNormalization(32))
model.add(df.ReLU())
model.add(df.SpatialMaxPoolingCUDNN(2, 2))
model.add(
df.SpatialConvolutionCUDNN(32,
64,
5,
5,
1,
1,
border='same',
with_bias=False))
model.add(df.BatchNormalization(64))
model.add(df.ReLU())
model.add(df.SpatialMaxPoolingCUDNN(2, 2))
model.add(df.Reshape(-1, 7 * 7 * 64))
model.add(df.Linear(7 * 7 * 64, 100, with_bias=False))
model.add(df.BatchNormalization(100))
model.add(df.ReLU())
model.add(df.Dropout(0.5))
model.add(df.Linear(100, 10))
model.add(df.SoftMax())
return model
def __init__(self, weightsname, *unused, **unused_kw):
self._net = df.Sequential( # 184x76
df.SpatialConvolution(3, 24, (3, 3)), # 182x74
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 24, (3, 3)), # 180x72
df.SpatialMaxPooling((3, 3)), # 60x24
df.BatchNormalization(24),
df.ReLU(),
df.SpatialConvolution(24, 48, (3, 3)), # 58x22
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 48, (3, 3)), # 56x20
df.SpatialMaxPooling((2, 2)), # 28x10
df.BatchNormalization(48),
df.ReLU(),
df.SpatialConvolution(48, 64, (3, 3)), # 26x8
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 3)), # 24x6
df.SpatialMaxPooling((2, 2)), # 12x3
df.BatchNormalization(64),
df.ReLU(),
df.SpatialConvolution(64, 64, (3, 2)), # 10x2
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64 * 10 * 2, 512),
df.ReLU(),
df.Dropout(0.5),
df.Linear(512, 2, init=df.init.normal(0.01)),
Biternion())
self._net.__setstate__(np.load(weightsname))
self._net.evaluate()
self._aug = AugmentationPipeline(None, None, Cropper((184, 76)))
def mknet(self, *outlayers):
return df.Sequential(
#df.SpatialConvolutionCUDNN(3,24,(3,3)),
df.SpatialConvolution(3, 24, (3, 3)),
df.BatchNormalization(24),
df.ReLU(),
#df.SpatialConvolutionCUDNN(24,24,(3,3)),
df.SpatialConvolution(24, 24, (3, 3)),
df.BatchNormalization(24),
#df.SpatialMaxPoolingCUDNN(2,2),
df.SpatialMaxPooling((2, 2)),
#df.MaxPooling(2,2),
df.ReLU(),
#df.SpatialConvolutionCUDNN(24,48,(3,3)),
df.SpatialConvolution(24, 48, (3, 3)),
df.BatchNormalization(48),
df.ReLU(),
# df.PoolingCUDNN()?
df.SpatialMaxPoolingCUDNN(48, 48, 3, 3),
#df.SpatialConvolution(48,48,(3,3)),
df.BatchNormalization(48),
df.SpatialMaxPooling((2, 2)),
df.ReLU(),
#df.SpatialConvolutionCUDNN(48,64,(3,3)),
df.SpatialConvolution(48, 64, (3, 3)),
df.BatchNormalization(64),
df.ReLU(),
#df.SpatialConvolutionCUDNN(64,64,(3,3)),
df.SpatialConvolution(64, 64, (3, 3)),
df.BatchNormalization(64),
df.ReLU(),
df.Dropout(0.2),
Flatten(),
df.Linear(64 * 5 * 5, 512),
df.ReLU(),
df.Dropout(0.5),
*outlayers)
def nnet():
model = df.Sequential()
model.add(df.AddConstant(1.0))
model.add(df.Log())
model.add(df.BatchNormalization(93))
model.add(df.Dropout(0.1))
model.add(df.Linear(93, 512))
model.add(df.BatchNormalization(512))
model.add(df.ReLU())
model.add(df.Dropout(0.5))
model.add(df.Linear(512, 512))
model.add(df.BatchNormalization(512))
model.add(df.ReLU())
model.add(df.Dropout(0.5))
model.add(df.Linear(512, 512))
model.add(df.BatchNormalization(512))
model.add(df.ReLU())
model.add(df.Dropout(0.5))
model.add(df.Linear(512, 9))
model.add(df.SoftMax())
return model
(trainX, trainY, trainNum), (testX, testY, testNum) = split(data,
label,
Number,
split=0.9)
#trainX,trainY = trainX.astype(df.floatX)/255,trainY.astype(df.floatX)
trainX, trainY = trainX.astype(np.float32) / 255, trainY.astype(np.float32)
#testX,testY = testX.astype(df.floatX)/255,testY.astype(df.floatX)
testX, testY = testX.astype(np.float32) / 255, testY.astype(np.float32)
pdb.set_trace()
################### Pure Linear Regression #######################
aug = AugmentationPipeline(trainX, trainY, Cropper((46, 46)))
#LinearTrain = [dotrain(net,df.MADCriterion(),aug,trainX,trainY[:,None]) for net in nets_shallow_linreg]
nets_shallow_linreg = [
df.Sequential(Flatten(),
df.Linear(3 * 46 * 46, 1, init=df.init.const(0)))
for _ in range(10)
]
LinearPred = [
Flatten().dopred_deg(net, aug, testX) for net in nets_shallow_linreg
]
Flatten().Error(LinearPred, testY[:, None])
pdb.set_trace()
#################### Deep Linear Regression ##################
nets_linreg = [
Flatten().mknet(df.Linear(512, 1, init=df.init.const(0)))
for _ in range(5)
]