def assertSuccess(self, input):
errors = Errors()
fl = Flatten(input, errors)
self.assertEquals(errors.num_errors, 0)
self.assertEquals(errors.num_warnings, 0)
inl = Inline(input, errors)
self.assertEquals(errors.num_errors, 0)
self.assertEquals(errors.num_warnings, 0)
def compile(self, data):
start_time = time.time()
self.ast = program_grammar.parseString(data, parseAll=True)[0]
print time.time() - start_time
start_time = time.time()
self.varcheck = VarCheck(self.ast, self.errors)
self.flatten = Flatten(self.ast, self.errors)
self.reduce = Reduce(self.ast, self.errors)
self.inline = Inline(self.ast, self.errors)
main_cfg = self.ast.symbol_table.lookup('main').cfg
print main_cfg
self.regalloc = RegisterAllocation(main_cfg)
self.lin = Linearise(self.ast, self.errors)
self.render = Render(self.lin.lines, self.errors)
print time.time() - start_time
return self.render.lines
def cnn_adam(X, Y, val_X, val_Y):
"""
CNN - ADAM
"""
model = Model(learning_rate=0.001,
batch_size=32,
epochs=200,
optimizer=Adam())
model.add(Conv2D(2, (3, 3), activation='tanh'))
model.add(Maxpool((2, 2), stride=2)) # 16x16
model.add(Dropout(0.5))
model.add(Conv2D(4, (3, 3), activation='tanh'))
model.add(Maxpool((2, 2), stride=2)) # 8x8
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(256, 32, activation='tanh'))
model.add(Dense(32, 1))
print("Begin Training")
model.train(X, Y, val_X, val_Y)
model.save_history("experiments/cnn-adam.csv")
def test_flatten_01(self):
f = Flatten()
res = f.flatten([1, 2, [4, 5]])
self.assertEqual(res, [1, 2, 4, 5])
def test_flatten_02(self):
f = Flatten()
res = f.flatten([1, 2, [4, 5], 6, [7, 8, [[9]]]])
self.assertEqual(res, [1, 2, 4, 5, 6, 7, 8, 9])
def __init__(self):
# Lenet
# input: 28x28
# conv1: (5x5x6)@s1p2 -> 28x28x6 {(28-5+2x2)/1+1}
# maxpool2: (2x2)@s2 -> 14x14x6 {(28-2)/2+1}
# conv3: (5x5x16)@s1p0 -> 10x10x16 {(14-5)/1+1}
# maxpool4: (2x2)@s2 -> 5x5x16 {(10-2)/2+1}
# conv5: (5x5x120)@s1p0 -> 1x1x120 {(5-5)/1+1}
# fc6: 120 -> 84
# fc7: 84 -> 10
# softmax: 10 -> 10
lr = 0.01
self.layers = []
self.layers.append(
ConvolutionLayer(inputs_channel=1,
num_filters=6,
width=5,
height=5,
padding=2,
stride=1,
learning_rate=lr,
name='conv1'))
self.layers.append(ReLu())
self.layers.append(
MaxPoolingLayer(width=2, height=2, stride=2, name='maxpool2'))
self.layers.append(
ConvolutionLayer(inputs_channel=6,
num_filters=16,
width=5,
height=5,
padding=0,
stride=1,
learning_rate=lr,
name='conv3'))
self.layers.append(ReLu())
self.layers.append(
MaxPoolingLayer(width=2, height=2, stride=2, name='maxpool4'))
self.layers.append(
ConvolutionLayer(inputs_channel=16,
num_filters=120,
width=5,
height=5,
padding=0,
stride=1,
learning_rate=lr,
name='conv5'))
self.layers.append(ReLu())
self.layers.append(Flatten())
self.layers.append(
FullyConnectedLayer(num_inputs=120,
num_outputs=84,
learning_rate=lr,
name='fc6'))
self.layers.append(ReLu())
self.layers.append(
FullyConnectedLayer(num_inputs=84,
num_outputs=10,
learning_rate=lr,
name='fc7'))
self.layers.append(Softmax())
self.lay_num = len(self.layers)
height_shift_range=0.16,
width_shift_range=0.16,
img_row_axis=1,
img_col_axis=2,
img_channel_axis=0,
horizontal_flip=True,
vertical_flip=False)
model.add_layer(ConvolutionalLayer(num_filters=32))
model.add_layer(Relu())
model.add_layer(
ConvolutionalLayer(input_shape=[32, 32, 32],
num_filters=32,
filter_dims=[32, 3, 3]))
model.add_layer(Relu())
model.add_layer(MaxPool())
model.add_layer(Flatten())
model.add_layer(Dense(input_shape=8192, neurons=650))
model.add_layer(Relu())
#model.add_layer(Dense(input_shape=1000,neurons=650))
#model.add_layer(Relu())
model.add_layer(Dense(input_shape=650, neurons=10))
model.add_layer(Softmax())
model.train()