print ' ', np.mean(c_4), str(corr_best[4][0]), min_cost[4], max_iter[4]
print ' ', np.mean(c_5), str(corr_best[5][0]), min_cost[5], max_iter[5]
print "[MESSAGE] The model is trained"
################################## BUILD SUPERVISED MODEL #######################################
pool_0=MaxPooling(pool_size=(2,2));
pool_1=MaxPooling(pool_size=(4,4));
pool_2=MaxPooling(pool_size=(2,2));
pool_3=MaxPooling(pool_size=(2,2));
pool_4=MaxPooling(pool_size=(2,2));
flattener=Flattener()
layer_6=ReLULayer(in_dim=64*1*1,
out_dim=32)
layer_7=SoftmaxLayer(in_dim=32,
out_dim=6)
model_sup=FeedForward(layers=[layer_0_en, pool_0, layer_1_en, pool_1, layer_2_en, pool_2, layer_3_en, pool_3, layer_4_en, pool_4, layer_5_en,
flattener, layer_6, layer_7])
out_sup=model_sup.fprop(images)
cost_sup=categorical_cross_entropy_cost(out_sup[-1], y)
updates=gd_updates(cost=cost_sup, params=model_sup.params, method="sgd", learning_rate=0.1)
train_sup=theano.function(inputs=[idx],
outputs=cost_sup,
updates=updates,
givens={X: train_set_x[idx * batch_size: (idx + 1) * batch_size],
print ' ', np.mean(c_3), str(
corr_best[3][0]), min_cost[3], max_iter[3]
print ' ', np.mean(c_4), str(
corr_best[4][0]), min_cost[4], max_iter[4]
print "[MESSAGE] The model is trained"
################################## BUILD SUPERVISED MODEL #######################################
pool_0 = MaxPooling(pool_size=(4, 4))
pool_1 = MaxPooling(pool_size=(2, 2))
pool_2 = MaxPooling(pool_size=(2, 2))
pool_3 = MaxPooling(pool_size=(2, 2))
flattener = Flattener()
layer_5 = ReLULayer(in_dim=128 * 1 * 1, out_dim=64)
layer_6 = SoftmaxLayer(in_dim=64, out_dim=10)
model_sup = FeedForward(layers=[
layer_0_en, pool_0, layer_1_en, pool_1, layer_2_en, pool_2, layer_3_en,
pool_3, layer_4_en, flattener, layer_5, layer_6
])
out_sup = model_sup.fprop(images)
cost_sup = categorical_cross_entropy_cost(out_sup[-1], y)
updates = gd_updates(cost=cost_sup,
params=model_sup.params,
method="sgd",
learning_rate=0.1)
train_sup = theano.function(
print ' ', np.mean(c_3), str(
corr_best[3][0]), min_cost[3], max_iter[3]
print ' ', np.mean(c_4), str(
corr_best[4][0]), min_cost[4], max_iter[4]
print "[MESSAGE] The model is trained"
################################## BUILD SUPERVISED MODEL #######################################
pool_0 = MaxPooling(pool_size=(4, 4))
pool_1 = MaxPooling(pool_size=(2, 2))
pool_2 = MaxPooling(pool_size=(2, 2))
pool_3 = MaxPooling(pool_size=(2, 2))
flattener = Flattener()
layer_5 = ReLULayer(in_dim=50 * 1 * 1, out_dim=25)
layer_6 = SoftmaxLayer(in_dim=25, out_dim=10)
model_sup = FeedForward(layers=[
layer_0_en, pool_0, layer_1_en, pool_1, layer_2_en, pool_2, layer_3_en,
pool_3, layer_4_en, flattener, layer_5, layer_6
])
out_sup = model_sup.fprop(images)
cost_sup = categorical_cross_entropy_cost(out_sup[-1], y)
updates = gd_updates(cost=cost_sup,
params=model_sup.params,
method="sgd",
learning_rate=0.1)
train_sup = theano.function(
print 'Training epoch %d, cost ' % epoch, np.mean(c_0), str(
corr_best[0][0]), min_cost[0], max_iter[0]
print ' ', np.mean(c_1), str(
corr_best[1][0]), min_cost[1], max_iter[1]
# print ' ' , np.mean(c_2), str(corr_best[2][0]), min_cost[2], max_iter[2]
# print ' ' , np.mean(c_3), str(corr_best[3][0]), min_cost[3], max_iter[3]
print "[MESSAGE] The model is trained"
################################## BUILD SUPERVISED MODEL #######################################
pool_0 = MaxPooling(pool_size=(2, 2))
pool_1 = MaxPooling(pool_size=(2, 2))
flattener = Flattener()
layer_2 = ReLULayer(in_dim=50 * 5 * 5, out_dim=500)
layer_3 = SoftmaxLayer(in_dim=500, out_dim=10)
# model_sup=FeedForward(layers=[layer_0_en, layer_1_en, flattener, layer_5, layer_6])
model_sup = FeedForward(layers=[
layer_0_en, pool_0, layer_1_en, pool_1, flattener, layer_2, layer_3
])
out_sup = model_sup.fprop(images)
cost_sup = categorical_cross_entropy_cost(out_sup[-1], y)
updates = gd_updates(cost=cost_sup,
params=model_sup.params,
method="sgd",
learning_rate=0.1)
train_sup = theano.function(
border_mode="full")
pool_0 = MaxPooling(pool_size=(2, 2))
layer_1 = LCNLayer(filter_size=(5, 5),
num_filters=32,
num_channels=64,
fm_size=(16, 16),
batch_size=batch_size,
border_mode="full")
pool_1 = MaxPooling(pool_size=(2, 2))
flattener = Flattener()
layer_2 = ReLULayer(in_dim=32 * 64, out_dim=800)
layer_3 = SoftmaxLayer(in_dim=800, out_dim=10)
model = FeedForward(
layers=[layer_0, pool_0, layer_1, pool_1, flattener, layer_2, layer_3])
out = model.fprop(images)
cost = categorical_cross_entropy_cost(out[-1], y)
updates = gd_updates(cost=cost,
params=model.params,
method="sgd",
learning_rate=0.01,
momentum=0.9)
extract = theano.function(
max_iter[1]=0
else:
max_iter[1]+=1
print 'Training epoch %d, cost ' % epoch, np.mean(c_0), str(corr_best[0][0]), min_cost[0], max_iter[0]
print ' ', np.mean(c_1), str(corr_best[1][0]), min_cost[1], max_iter[1]
print "[MESSAGE] The model is trained"
################################## BUILD SUPERVISED MODEL #######################################
pool_0=MaxPooling(pool_size=(4,4));
pool_1=MaxPooling(pool_size=(2,2));
flattener=Flattener()
layer_2=ReLULayer(in_dim=50*4*4,
out_dim=400)
layer_3=SoftmaxLayer(in_dim=400,
out_dim=10)
model_sup=FeedForward(layers=[layer_0_en, pool_0, layer_1_en, pool_1, flattener, layer_2, layer_3])
out_sup=model_sup.fprop(images)
cost_sup=categorical_cross_entropy_cost(out_sup[-1], y)
updates=gd_updates(cost=cost_sup, params=model_sup.params, method="sgd", learning_rate=0.1)
train_sup=theano.function(inputs=[idx],
outputs=cost_sup,
updates=updates,
givens={X: train_set_x[idx * batch_size: (idx + 1) * batch_size],
y: train_set_y[idx * batch_size: (idx + 1) * batch_size]})
print 'Training epoch %d, cost ' % epoch, np.mean(c_0), str(
corr_best[0][0]), min_cost[0], max_iter[0]
print ' ', np.mean(c_1), str(
corr_best[1][0]), min_cost[1], max_iter[1]
print ' ', np.mean(c_2), str(
corr_best[2][0]), min_cost[2], max_iter[2]
print ' ', np.mean(c_3), str(
corr_best[3][0]), min_cost[3], max_iter[3]
print "[MESSAGE] The model is trained"
################################## BUILD SUPERVISED MODEL #######################################
flattener = Flattener()
layer_5 = ReLULayer(in_dim=50 * 16 * 16, out_dim=1000)
layer_6 = SoftmaxLayer(in_dim=1000, out_dim=10)
model_sup = FeedForward(layers=[
layer_0_en, layer_1_en, layer_2_en, layer_3_en, flattener, layer_5, layer_6
])
out_sup = model_sup.fprop(images)
cost_sup = categorical_cross_entropy_cost(out_sup[-1], y)
updates = gd_updates(cost=cost_sup,
params=model_sup.params,
method="sgd",
learning_rate=0.1)
train_sup = theano.function(
inputs=[idx],