from OkapiV2.Core import Model, Branch
from OkapiV2.Layers.Basic import FullyConnected
from OkapiV2.Layers.Activations import ActivationLayer, PReLULayer
from OkapiV2 import Activations, Datasets, Optimizers
x_train, y_train, x_val, y_val, x_test, y_test = Datasets.load_mnist()
tree = Branch()
tree.add_layer(FullyConnected((512, 1, 1, 1)))
tree.add_layer(PReLULayer())
tree.add_layer(FullyConnected((512, 1, 1, 1)))
tree.add_layer(PReLULayer())
tree.add_layer(FullyConnected((512, 1, 1, 1)))
tree.add_layer(PReLULayer())
tree.add_layer(FullyConnected())
tree.add_layer(ActivationLayer(Activations.softmax))
tree.add_input(x_train)
model = Model()
model.set_tree(tree)
model.set_optimizer(Optimizers.RMSprop(learning_rate=0.00005))
index = 60000
model.train([x_train[:index, :, :, :]], y_train[:index, :], 24)
accuracy = model.get_accuracy([x_train[:index, :, :, :]], y_train[:index])
print("Accuracy: {}%".format(accuracy))
test_accuracy = model.get_accuracy([x_test], y_test)
print("Test accuracy: {}%".format(test_accuracy))
sentences.append(text[i: i + maxlen])
next_chars.append(text[i + maxlen])
print('nb sequences:', len(sentences))
print('Vectorization...')
X = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
y = np.zeros((len(sentences), len(chars)), dtype=np.bool)
for i, sentence in enumerate(sentences):
for t, char in enumerate(sentence):
X[i, t, char_indices[char]] = 1
y[i, char_indices[next_chars[i]]] = 1
# build the model: 2 stacked LSTM
print('Build model...')
tree = Branch()
tree.add_layer(LSTM((512, 1, 1, 1), return_sequences=True))
tree.add_layer(Dropout(0.2))
tree.add_layer(LSTM((512, 1, 1, 1), return_sequences=False))
tree.add_layer(Dropout(0.2))
tree.add_layer(FullyConnected())
tree.add_layer(ActivationLayer(Activations.softmax))
tree.add_input(X)
model = Model()
model.set_tree(tree)
def sample(a, temperature=1.0):
# helper function to sample an index from a probability array
a = np.log(a) / temperature
a = np.exp(a) / np.sum(np.exp(a))
def main_okapi():
from OkapiV2.Core import Model, Branch
from OkapiV2.Layers.Basic import FullyConnected, Dropout
from OkapiV2.Layers.Activations import ActivationLayer, PReLULayer
from OkapiV2.Layers.Convolutional import Convolutional, MaxPooling
from OkapiV2 import Activations, Datasets
from OkapiV2 import Optimizers
X_train, y_train, X_val, y_val, X_test, y_test = Datasets.load_mnist()
tree = Branch()
tree.add_layer(Convolutional(num_filters, filter_size, filter_size, pad=pad))
# tree.add_layer(BatchNorm())
tree.add_layer(PReLULayer())
tree.add_layer(MaxPooling(pool_size, pool_size))
tree.add_layer(Convolutional(num_filters, filter_size, filter_size, pad=pad))
# tree.add_layer(BatchNorm())
tree.add_layer(PReLULayer())
tree.add_layer(MaxPooling(pool_size, pool_size))
tree.add_layer(Convolutional(num_filters, filter_size, filter_size, pad=pad))
# tree.add_layer(BatchNorm())
tree.add_layer(PReLULayer())
tree.add_layer(MaxPooling(pool_size, pool_size))
'''tree.add_layer(Convolutional(num_filters, filter_size, filter_size, pad=pad))
# tree.add_layer(BatchNorm())
tree.add_layer(PReLULayer())
tree.add_layer(MaxPooling(pool_size, pool_size))'''
'''tree.add_layer(Dropout(0.25))
tree.add_layer(FullyConnected((h_size, 1, 1, 1)))
tree.add_layer(PReLULayer())
# tree.add_layer(BatchNorm())'''
tree.add_layer(Dropout(0.5))
tree.add_layer(FullyConnected())
tree.add_layer(ActivationLayer(Activations.alt_softmax))
tree.add_input(X_train)
model = Model()
model.set_tree(tree)
model.set_optimizer(Optimizers.RMSprop(learning_rate=learning_rate,
momentum=momentum))
model.train([X_train], y_train, num_epochs=num_epochs,
batch_size=batch_size)
# ok.save_model(model, 'okapi_mnist.pk')
okapi_accuracy = model.get_accuracy([X_test], y_test)
print("Test Accuracy: {}%"
.format(round(okapi_accuracy, 2)))
return okapi_accuracy
X_train, y_train, X_val, y_val, X_test, y_test = Datasets.load_mnist() X_obs, y_obs = X_train, y_train X_reward = [] X_reward.append(np.zeros((X_obs.shape[0] * 10, X_obs.shape[1], X_obs.shape[2], X_obs.shape[3]))) X_reward.append(np.zeros((X_obs.shape[0] * 10, y_obs.shape[1]))) y_reward = np.zeros((X_obs.shape[0] * 10, 1)) dropout_p = 0.2 num_filters = 32 filter_size = 3 pool_size = 2 num_classes = 10 pad = True state_branch = Branch() state_branch.add_layer(Convolutional(num_filters, filter_size, filter_size, pad=pad)) state_branch.add_layer(PReLULayer()) state_branch.add_layer(MaxPooling(pool_size, pool_size)) state_branch.add_layer(Convolutional(num_filters, filter_size, filter_size, pad=pad)) state_branch.add_layer(PReLULayer()) state_branch.add_layer(MaxPooling(pool_size, pool_size)) state_branch.add_layer(FullyConnected((100, 1, 1, 1))) state_branch.add_layer(ActivationLayer(Activations.tanh)) state_branch.add_input(X_reward[0]) action_branch = Branch() action_branch.add_layer(FullyConnected((100, 1, 1, 1))) action_branch.add_layer(PReLULayer()) action_branch.add_input(X_reward[1])
