test_output = lasagne.layers.get_output(mlp, deterministic=True)
test_loss = T.mean(T.sqr(T.maximum(0., 1. - target * test_output)))
test_err = T.mean(T.neq(T.argmax(test_output, axis=1),
T.argmax(target, axis=1)),
dtype=theano.config.floatX)
# Compile a function performing a training step on a mini-batch (by giving the updates dictionary)
# and returning the corresponding training loss:
train_fn = theano.function([input, target, LR], loss, updates=updates)
# Compile a second function computing the validation loss and accuracy:
val_fn = theano.function([input, target], [test_loss, test_err])
print('Training...')
binary_connect.train(train_fn, val_fn, batch_size, LR_start, LR_decay,
num_epochs, train_set.X, train_set.y, valid_set.X,
valid_set.y, test_set.X, test_set.y)
# print("display histogram")
# W = lasagne.layers.get_all_layers(mlp)[2].W.get_value()
# print(W.shape)
# histogram = np.histogram(W,bins=1000,range=(-1.1,1.1))
# np.savetxt(str(dropout_hidden)+str(binary)+str(stochastic)+str(H)+"_hist0.csv", histogram[0], delimiter=",")
# np.savetxt(str(dropout_hidden)+str(binary)+str(stochastic)+str(H)+"_hist1.csv", histogram[1], delimiter=",")
# Optionally, you could now dump the network weights to a file like this:
# np.savez('model.npz', lasagne.layers.get_all_param_values(network))
test_loss = T.mean(T.sqr(T.maximum(0., 1. - target * test_output)))
test_err = T.mean(T.neq(T.argmax(test_output, axis=1),
T.argmax(target, axis=1)),
dtype=theano.config.floatX)
# Compile a function performing a training step on a mini-batch (by giving the updates dictionary)
# and returning the corresponding training loss:
train_fn = theano.function([input, target, LR], loss, updates=updates)
# Compile a second function computing the validation loss and accuracy:
val_fn = theano.function([input, target], [test_loss, test_err])
print('Training...')
binary_connect.train(train_fn, val_fn, batch_size, LR_start, LR_decay, 200,
train_images, train_labels, valid_images,
valid_labels, test_images, test_labels)
# store the weights value and bias value of each binaryDenselayer
from six.moves import cPickle as pickle
print(lasagne.layers.get_all_params(mlp))
para = lasagne.layers.get_all_param_values(mlp)
weights = []
means = []
stds = []
for i in range(0, 24, 6):
weights.append(para[i])
means.append(para[i + 2])
stds.append(para[i + 3])
# save the values to a pickle file in order to construct thr model of tensorflow framework
loss_or_grads=loss, params=params, learning_rate=LR).items())
else:
params = lasagne.layers.get_all_params(cnn, trainable=True)
updates = lasagne.updates.adam(loss_or_grads=loss,
params=params,
learning_rate=LR)
test_output = lasagne.layers.get_output(cnn, deterministic=True)
test_loss = T.mean(T.sqr(T.maximum(0., 1. - target * test_output)))
test_err = T.mean(T.neq(T.argmax(test_output, axis=1),
T.argmax(target, axis=1)),
dtype=theano.config.floatX)
# Compile a function performing a training step on a mini-batch (by giving the updates dictionary)
# and returning the corresponding training loss:
train_fn = theano.function([input, target, LR], loss, updates=updates)
# Compile a second function computing the validation loss and accuracy:
val_fn = theano.function([input, target], [test_loss, test_err])
print('Training...')
print(gates.train.X.shape)
binary_connect.train(train_fn, val_fn, batch_size, LR_start, LR_decay,
num_epochs, gates.train.X, gates.train.Y,
gates.valid.X, gates.valid.Y, gates.test.X,
gates.test.Y)
np.savez('model_all.npz', lasagne.layers.get_all_param_values(cnn))
