def conv_detector(X):
n_detectors_layer_1 = 20
n_detectors_layer_2 = 30
n = X.shape[0]
input = pad(X)
w1 = init_weights((n_detectors_layer_1, 1, 4, 4), name="weights_layer_1", scale=0.1)
w2 = init_weights((n_detectors_layer_2, n_detectors_layer_1, 4, 4), name="weights_layer_2")
h1 = rectify(conv2d(input.reshape((n, 1, 7, 16)), w1, border_mode='valid', subsample=(1, 4)))
input_2 = h1.reshape((n, n_detectors_layer_1, 1, 16))
h2 = rectify(conv2d(pad(input_2, axis=3).reshape((n, n_detectors_layer_1, 7, 16)), w2, border_mode='valid', subsample=(1, 4)))
output = h2.reshape((n, 4*4*n_detectors_layer_2))
return output, [w1, w2]
def jet_detector(X):
n_detectors_layer_1 = 5
n_jets_layer_1 = 4
n_detectors_layer_2 = 5
n_jets_layer_2 = 4
# Takes 16 dim vector, applies W to it, returns resultant vector
def apply_detector(W, jet, n_jets):
map_i = []
for start, end in zip(range(0, 16, n_jets), range(4, 16+4, n_jets)):
map_i.append(rectify(T.dot(W, jet[start:end])))
return T.concatenate(map_i, axis=0)
detectors_layer_1 = []
# Initialize weights
for i in range(n_detectors_layer_1):
detectors_layer_1.append(init_weights((4, 4), name="weights_layer_1_{0}".format(i)), scale=0.1)
maps_layer_1 = []
for W in detectors_layer_1:
map_i = apply_detector(W, X.T, n_jets_layer_1)
maps_layer_1.append(map_i)
detectors_layer_2 = []
# Initialize weights
for i in range(n_detectors_layer_2):
detectors_layer_2.append(init_weights((4, 4), name="weights_layer_2_{0}".format(i)))
maps_layer_2 = []
for map in maps_layer_1:
for W in detectors_layer_2:
map_i = apply_detector(W, map, n_jets_layer_2)
maps_layer_2.append(map_i)
jet_detector_output = T.concatenate(maps_layer_2, axis=0)
params = detectors_layer_1 + detectors_layer_2
return jet_detector_output.T, params
# trX, trY = load_data()
trX = trX[0:500000]
trY = trY[0:500000]
# vX, vY = load_data('valid')
vX = vX[0:10000]
vY = vY[0:10000]
X = T.fmatrix()
Y = T.fmatrix()
w_h = theano.shared(floatX(np.random.randn(*(28, 300)) * 0.1))
b_h = theano.shared(value=np.zeros((300, ), dtype=theano.config.floatX),
name='b_h',
borrow=True)
w_h2 = init_weights((300, 300))
b_h2 = theano.shared(value=np.zeros((300, ), dtype=theano.config.floatX),
name='b_h2',
borrow=True)
w_h3 = init_weights((300, 300))
b_h3 = theano.shared(value=np.zeros((300, ), dtype=theano.config.floatX),
name='b_h3',
borrow=True)
w_h4 = init_weights((300, 300))
b_h4 = theano.shared(value=np.zeros((300, ), dtype=theano.config.floatX),
name='b_h4',
borrow=True)
w_o = theano.shared(floatX(np.random.randn(*(300, 1)) * 0.001))
b_o = theano.shared(value=np.zeros((1, ), dtype=theano.config.floatX),
name='b_o',
borrow=True)
epochs = 5
X = T.fmatrix('X')
epsilon = T.fmatrix()
# Make random crop from X
crop_mask, updates = theano.scan(fn=random_crop, sequences=[X])
crop_X = X * crop_mask
# Creating the masks
reconstruction_dims, updates = theano.scan(fn=MASK_blanking, sequences=[crop_X])
prediction_dims = crop_mask - reconstruction_dims
# model(input_data, epsilon, w_h, mu_w, sig_w, w_h2, w_o, b_h, mu_b, sig_b, b_h2, b_o):
# Initialize Weights
weights_layer_1 = init_weights((n_visible_units, n_hidden_units), name='weights_layer_1')
bias_layer_1 = init_biases(n_hidden_units, name='bias_layer_1')
weights_layer_mu = init_weights((n_hidden_units, n_z), name='weights_layer_mu')
bias_layer_mu = init_biases(n_z, name='bias_layer_mu')
weights_layer_sig = init_weights((n_hidden_units, n_z), name='weights_layer_sig')
bias_layer_sig = init_biases(n_z, name='bias_layer_sig')
weights_layer_2 = init_weights((n_z, n_hidden_units), name='weights_layer_2')
bias_layer_2 = init_biases(n_hidden_units, name='bias_layer_2')
weights_layer_y = init_weights((n_hidden_units, n_visible_units), name='weights_layer_y')
bias_layer_y = init_biases(n_visible_units, name='bias_layer_y')
# Build Model
model_input = crop_X * reconstruction_dims
X_hat, mu, sig = model(model_input, epsilon, weights_layer_1, weights_layer_mu, weights_layer_sig, weights_layer_2,
weights_layer_y, bias_layer_1, bias_layer_mu, bias_layer_sig, bias_layer_2, bias_layer_y)
output = T.nnet.sigmoid(T.dot(h1, w_o) + b_y)
return output
# Define parameters
learning_rate = 0.1
n_hidden_units = 100
n_visible_units = 784
blank_proportion = .1
alpha = .5
batch_size = 100
epochs = 10
X = T.fmatrix('X')
# Initialize Weights
weights_layer_1 = init_weights((n_visible_units, n_hidden_units), name='weights_layer_1')
bias_layer_1 = init_biases(n_hidden_units, name='bias_layer_1')
weights_layer_y = init_weights((n_hidden_units, n_visible_units), name='weights_layer_y')
bias_layer_y = init_biases(n_visible_units, name='bias_layer_y')
# Build Model
X_hat = model(X, weights_layer_1, weights_layer_y, bias_layer_1, bias_layer_y)
# Loss
L = - T.sum(X * T.log(X_hat) + (1 - X) * T.log(1 - X_hat), axis=1)
loss = T.mean(L)
# Parameter Updating
params = [weights_layer_y, bias_layer_y, weights_layer_1, bias_layer_1]
updates = sgd(loss, params, lr=learning_rate)
return output
# Define parameters
learning_rate = 0.1
n_hidden_units = 100
n_visible_units = 784
blank_proportion = .1
alpha = .5
batch_size = 100
epochs = 10
X = T.fmatrix('X')
# Initialize Weights
weights_layer_1 = init_weights((n_visible_units, n_hidden_units),
name='weights_layer_1')
bias_layer_1 = init_biases(n_hidden_units, name='bias_layer_1')
weights_layer_y = init_weights((n_hidden_units, n_visible_units),
name='weights_layer_y')
bias_layer_y = init_biases(n_visible_units, name='bias_layer_y')
# Build Model
X_hat = model(X, weights_layer_1, weights_layer_y, bias_layer_1, bias_layer_y)
# Loss
L = -T.sum(X * T.log(X_hat) + (1 - X) * T.log(1 - X_hat), axis=1)
loss = T.mean(L)
# Parameter Updating
params = [weights_layer_y, bias_layer_y, weights_layer_1, bias_layer_1]
updates = sgd(loss, params, lr=learning_rate)
x = np.zeros((112, ))
x[48:64] = np.arange(16)
x = x.reshape(-1, 1, 7, 16)
f(x).shape
jets = T.fmatrix('Jets')
lepton_missing_E = T.fmatrix('lepton_and_missing_energy')
high_level = T.fmatrix('high_level')
n_input_units = 28
n_hidden_units = 300
n_output_units = 1
# Initialize Weights
w_h = init_weights((n_input_units, n_hidden_units),
name='weights_layer_1',
scale=0.1)
b_h = init_biases(n_hidden_units, name='bias_layer_1')
w_h2 = init_weights((n_hidden_units, n_hidden_units), name='weights_layer_2')
b_h2 = init_biases(n_hidden_units, name='bias_layer_2')
w_h3 = init_weights((n_hidden_units, n_hidden_units), name='weights_layer_3')
b_h3 = init_biases(n_hidden_units, name='bias_layer_3')
w_h4 = init_weights((n_hidden_units, n_hidden_units), name='weights_layer_4')
b_h4 = init_biases(n_hidden_units, name='bias_layer_4')
w_o = init_weights((n_hidden_units, n_output_units),
name='weights_layer_y',
scale=0.001)
b_o = init_biases(n_output_units, name='bias_layer_y')
noise_h, noise_h2, noise_h3, noise_h4, noise_py_x = model(
X, w_h, w_h2, w_h3, w_h4, w_o, b_h, b_h2, b_h3, b_h4, b_o, 0.8,
trX = trX[0:500000]
trY = trY[0:500000]
# vX, vY = load_data('valid')
vX = vX[0:10000]
vY = vY[0:10000]
jets = T.fmatrix('jets')
other_features = T.fmatrix('other_features')
Y = T.fmatrix()
w_h = theano.shared(floatX(np.random.randn(*(12, 100)) * 0.1),
name="fc_weights_layer_1")
b_h = theano.shared(value=np.zeros((100, ), dtype=theano.config.floatX),
name='b_h',
borrow=True)
w_h2 = init_weights((100, 100), name="fc_weights_layer_2")
b_h2 = theano.shared(value=np.zeros((100, ), dtype=theano.config.floatX),
name='b_h2',
borrow=True)
w_h3 = init_weights((580, 300), name="fc_weights_layer_3")
b_h3 = theano.shared(value=np.zeros((300, ), dtype=theano.config.floatX),
name='b_h3',
borrow=True)
w_h4 = init_weights((300, 300), name="fc_weights_layer_4")
b_h4 = theano.shared(value=np.zeros((300, ), dtype=theano.config.floatX),
name='b_h4',
borrow=True)
w_o = theano.shared(floatX(np.random.randn(*(300, 1)) * 0.001),
name="fc_weights_layer_o")
b_o = theano.shared(value=np.zeros((1, ), dtype=theano.config.floatX),
name='b_o',