tasks = sample_tasks(dim, difficulties)
print(tasks)
network = MLP(
input_shape=(in_dim, ),
output_dim=out_dim,
hidden_sizes=hidden_size,
hidden_nonlinearity=NL.tanh,
output_nonlinearity=None,
)
out_var = TT.matrix('out_var')
prediction = network._output
loss = lasagne.objectives.squared_error(prediction, out_var)
loss = loss.mean()
params = network.get_params(trainable=True)
updates = lasagne.updates.adam(loss, params, learning_rate=0.001)
train_fn = T.function([network.input_layer.input_var, out_var],
loss,
updates=updates,
allow_input_downcast=True)
ls = TT.mean((prediction - out_var)**2)
grad = T.grad(ls, params, disconnected_inputs='warn')
grad_fn = T.function([network.input_layer.input_var, out_var],
grad,
allow_input_downcast=True)
loss_fn = T.function([network.input_layer.input_var, out_var],
loss,
allow_input_downcast=True)
out = T.function([network.input_layer.input_var],
prediction,
tasks = sample_tasks(dim, difficulties)
print(tasks)
network = MLP(
input_shape=(in_dim,),
output_dim=out_dim,
hidden_sizes=hidden_size,
hidden_nonlinearity=NL.tanh,
output_nonlinearity=None,
)
out_var = TT.matrix('out_var')
prediction = network._output
loss = lasagne.objectives.squared_error(prediction, out_var)
loss = loss.mean()
params = network.get_params(trainable=True)
updates = lasagne.updates.sgd(loss, params, learning_rate=0.002)
train_fn = T.function([network.input_layer.input_var, out_var], loss, updates=updates, allow_input_downcast=True)
ls = TT.mean((prediction - out_var)**2)
grad = T.grad(ls, params, disconnected_inputs='warn')
grad_fn = T.function([network.input_layer.input_var, out_var], grad, allow_input_downcast=True)
loss_fn = T.function([network.input_layer.input_var, out_var], loss, allow_input_downcast=True)
out = T.function([network.input_layer.input_var], prediction, allow_input_downcast=True)
Xs, Ys = synthesize_data(dim, 2000, tasks)
train(train_fn, np.concatenate(Xs), np.concatenate(Ys), init_epochs)
print('------- initial training complete ---------------')
init_param_value = np.copy(network.get_param_values())
Xs, Ys = synthesize_data(dim, 2000, tasks)
tasks = sample_tasks(dim, difficulties)
print(tasks)
network = MLP(
input_shape=(in_dim, ),
output_dim=out_dim,
hidden_sizes=hidden_size,
hidden_nonlinearity=NL.tanh,
output_nonlinearity=None,
)
out_var = TT.matrix('out_var')
prediction = network._output
loss = lasagne.objectives.squared_error(prediction, out_var)
loss = loss.mean()
params = network.get_params(trainable=True)
updates = lasagne.updates.sgd(loss, params, learning_rate=0.002)
train_fn = T.function([network.input_layer.input_var, out_var],
loss,
updates=updates,
allow_input_downcast=True)
ls = TT.mean((prediction - out_var)**2)
grad = T.grad(ls, params, disconnected_inputs='warn')
grad_fn = T.function([network.input_layer.input_var, out_var],
grad,
allow_input_downcast=True)
loss_fn = T.function([network.input_layer.input_var, out_var],
loss,
allow_input_downcast=True)
out = T.function([network.input_layer.input_var],
prediction,
tasks = sample_tasks(dim, difficulties)
network = MLP(
input_shape=(in_dim, ),
output_dim=out_dim,
hidden_sizes=hidden_size,
hidden_nonlinearity=NL.tanh,
output_nonlinearity=None,
)
out_var = TT.matrix('out_var')
prediction = network._output
loss = lasagne.objectives.squared_error(prediction, out_var)
loss = loss.mean()
params = network.get_params(trainable=True)
updates = lasagne.updates.adam(loss, params, learning_rate=0.002)
train_fn = T.function([network.input_layer.input_var, out_var],
loss,
updates=updates,
allow_input_downcast=True)
ls = TT.mean((prediction - out_var)**2)
grad = T.grad(ls, params, disconnected_inputs='warn')
grad_fn = T.function([network.input_layer.input_var, out_var],
grad,
allow_input_downcast=True)
loss_fn = T.function([network.input_layer.input_var, out_var],
loss,
allow_input_downcast=True)
out = T.function([network.input_layer.input_var],
prediction,
