Example #1
1
def test_sequential_model_saving_2():
    # test with funkier config
    model = Sequential()
    model.add(Dense(2, input_dim=3))
    model.add(RepeatVector(3))
    model.add(TimeDistributed(Dense(3)))
    model.compile(loss=objectives.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy],
                  sample_weight_mode='temporal')
    x = np.random.random((1, 3))
    y = np.random.random((1, 3, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    fname = 'tmp_' + str(np.random.randint(10000)) + '.h5'
    save_model(model, fname)

    new_model = load_model(fname)
    os.remove(fname)

    out2 = new_model.predict(x)
    assert_allclose(out, out2, atol=1e-05)

    # test that new updates are the same with both models
    x = np.random.random((1, 3))
    y = np.random.random((1, 3, 3))
    model.train_on_batch(x, y)
    new_model.train_on_batch(x, y)
    out = model.predict(x)
    out2 = new_model.predict(x)
    assert_allclose(out, out2, atol=1e-05)
Example #2
0
def test_sequential_model_saving():
    model = Sequential()
    model.add(Dense(2, input_shape=(3,)))
    model.add(RepeatVector(3))
    model.add(TimeDistributed(Dense(3)))
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy],
                  sample_weight_mode='temporal')
    x = np.random.random((1, 3))
    y = np.random.random((1, 3, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    new_model = load_model(fname)
    os.remove(fname)

    out2 = new_model.predict(x)
    assert_allclose(out, out2, atol=1e-05)

    # test that new updates are the same with both models
    x = np.random.random((1, 3))
    y = np.random.random((1, 3, 3))
    model.train_on_batch(x, y)
    new_model.train_on_batch(x, y)
    out = model.predict(x)
    out2 = new_model.predict(x)
    assert_allclose(out, out2, atol=1e-05)
Example #3
0
def test_merge_overlap():
    left = Sequential()
    left.add(Dense(nb_hidden, input_shape=(input_dim,)))
    left.add(Activation('relu'))

    model = Sequential()
    model.add(Merge([left, left], mode='sum'))
    model.add(Dense(nb_class))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

    model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch, show_accuracy=True, verbose=1, validation_data=(X_test, y_test))
    model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch, show_accuracy=False, verbose=2, validation_data=(X_test, y_test))
    model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch, show_accuracy=True, verbose=2, validation_split=0.1)
    model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch, show_accuracy=False, verbose=1, validation_split=0.1)
    model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=0)
    model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=1, shuffle=False)

    model.train_on_batch(X_train[:32], y_train[:32])

    loss = model.evaluate(X_train, y_train, verbose=0)
    assert(loss < 0.7)
    model.predict(X_test, verbose=0)
    model.predict_classes(X_test, verbose=0)
    model.predict_proba(X_test, verbose=0)
    model.get_config(verbose=0)

    fname = 'test_merge_overlap_temp.h5'
    model.save_weights(fname, overwrite=True)
    model.load_weights(fname)
    os.remove(fname)

    nloss = model.evaluate(X_train, y_train, verbose=0)
    assert(loss == nloss)
Example #4
0
def test_nested_sequential(in_tmpdir):
    (x_train, y_train), (x_test, y_test) = _get_test_data()

    inner = Sequential()
    inner.add(Dense(num_hidden, input_shape=(input_dim,)))
    inner.add(Activation('relu'))
    inner.add(Dense(num_class))

    middle = Sequential()
    middle.add(inner)

    model = Sequential()
    model.add(middle)
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

    model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_test, y_test))
    model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=2, validation_split=0.1)
    model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=0)
    model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, shuffle=False)

    model.train_on_batch(x_train[:32], y_train[:32])

    loss = model.evaluate(x_test, y_test, verbose=0)

    model.predict(x_test, verbose=0)
    model.predict_classes(x_test, verbose=0)
    model.predict_proba(x_test, verbose=0)

    fname = 'test_nested_sequential_temp.h5'
    model.save_weights(fname, overwrite=True)

    inner = Sequential()
    inner.add(Dense(num_hidden, input_shape=(input_dim,)))
    inner.add(Activation('relu'))
    inner.add(Dense(num_class))

    middle = Sequential()
    middle.add(inner)

    model = Sequential()
    model.add(middle)
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
    model.load_weights(fname)
    os.remove(fname)

    nloss = model.evaluate(x_test, y_test, verbose=0)
    assert(loss == nloss)

    # test serialization
    config = model.get_config()
    Sequential.from_config(config)

    model.summary()
    json_str = model.to_json()
    model_from_json(json_str)

    yaml_str = model.to_yaml()
    model_from_yaml(yaml_str)
Example #5
0
def test_sequential_model_saving():
    model = Sequential()
    model.add(Dense(2, input_dim=3))
    model.add(Dense(3))
    model.compile(loss='mse', optimizer='rmsprop', metrics=['acc'])

    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    fname = 'tmp_' + str(np.random.randint(10000)) + '.h5'
    save_model(model, fname)

    new_model = load_model(fname)

    out2 = new_model.predict(x)
    assert_allclose(out, out2, atol=1e-05)

    # test that new updates are the same with both models
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)
    new_model.train_on_batch(x, y)
    out = model.predict(x)
    out2 = new_model.predict(x)
    assert_allclose(out, out2, atol=1e-05)

    # test load_weights on model file
    model.load_weights(fname)
    os.remove(fname)
def save_bottleneck_features():
    model = Sequential()
    model.add(Convolution2D(32, 3, 3, input_shape=(1, img_width, img_height)))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.1))

    model.add(Convolution2D(64, 2, 2))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))

    model.add(Convolution2D(128, 2, 2))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.3))

    assert os.path.exists(weights_path), 'Model weights not found (see "weights_path" variable in script).'
    f = h5py.File(weights_path)
    layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
    weight_value_tuples = []
    for k, name in enumerate(layer_names):
        if k >= len(model.layers):
            break
        g = f[name]
        weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
        if len(weight_names):
            weight_values = [g[weight_name] for weight_name in weight_names]
            layer = model.layers[k]
            symbolic_weights = layer.trainable_weights + layer.non_trainable_weights
            if len(weight_values) != len(symbolic_weights):
                raise Exception('Layer #' + str(k) +
                                ' (named "' + layer.name +
                                '" in the current model) was found to '
                                'correspond to layer ' + name +
                                ' in the save file. '
                                'However the new layer ' + layer.name +
                                ' expects ' + str(len(symbolic_weights)) +
                                ' weights, but the saved weights have ' +
                                str(len(weight_values)) +
                                ' elements.')
            weight_value_tuples += zip(symbolic_weights, weight_values)
    K.batch_set_value(weight_value_tuples)
    f.close()
    print('Model loaded.')

    X, y = load2d()
    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
    X_flipped, y_flipped = flip_image(X_train, y_train)

    X_train = np.vstack((X_train, X_flipped))
    y_train = np.vstack((y_train, y_flipped))

    bottleneck_features_train = model.predict(X_train)
    np.save(open('bottleneck_features_train.npy', 'w'), bottleneck_features_train)
    np.save(open('label_train.npy', 'w'), y_train)

    bottleneck_features_validation = model.predict(X_val)
    np.save(open('bottleneck_features_validation.npy', 'w'), bottleneck_features_validation)
    np.save(open('label_validation.npy', 'w'), y_val)
Example #7
0
def test_recursive():
    # test layer-like API

    graph = containers.Graph()
    graph.add_input(name='input1', input_shape=(32,))
    graph.add_node(Dense(16), name='dense1', input='input1')
    graph.add_node(Dense(4), name='dense2', input='input1')
    graph.add_node(Dense(4), name='dense3', input='dense1')
    graph.add_output(name='output1', inputs=['dense2', 'dense3'],
                     merge_mode='sum')

    seq = Sequential()
    seq.add(Dense(32, input_shape=(32,)))
    seq.add(graph)
    seq.add(Dense(4))

    seq.compile('rmsprop', 'mse')

    seq.fit(X_train_graph, y_train_graph, batch_size=10, nb_epoch=10)
    loss = seq.evaluate(X_test_graph, y_test_graph)
    assert(loss < 2.5)

    loss = seq.evaluate(X_test_graph, y_test_graph, show_accuracy=True)
    seq.predict(X_test_graph)
    seq.get_config(verbose=1)
Example #8
0
def _test_smoke(channel_order=None):

    from kfs.layers.convolutional import Convolution2DEnergy_TemporalBasis
    from keras.models import Sequential
    #from keras.layers import Flatten, Dense
    input_shape = (12, 3, 64, 64)
    if channel_order is None:
        channel_order = K.image_data_format()
    if channel_order == 'channels_last':
        input_shape = (12, 64, 64, 3)

    rng = np.random.RandomState(42)
    datums = rng.randn(6, 12, 3, 64, 64).astype('float32')
    if channel_order == 'channels_last':
        datums = datums.transpose(0, 1, 3, 4, 2)

    nn2 = Sequential()
    nn2.add(Convolution2DEnergy_TemporalCorrelation(8, 16, 4, (5, 5), 7,
                                            padding='same',
                                            temporal_kernel_size=5,
                                            input_shape=input_shape))
    nn2.compile(loss='mse', optimizer='sgd')

    pred2 = nn2.predict(datums)

    return nn2, nn2.predict(datums)
Example #9
0
def test_autoencoder_advanced():
    encoder = containers.Sequential([core.Dense(5, input_shape=(10,))])
    decoder = containers.Sequential([core.Dense(10, input_shape=(5,))])
    X_train = np.random.random((100, 10))
    X_test = np.random.random((100, 10))

    model = Sequential()
    model.add(core.Dense(output_dim=10, input_dim=10))
    autoencoder = core.AutoEncoder(encoder=encoder, decoder=decoder,
                                   output_reconstruction=True)
    model.add(autoencoder)

    # training the autoencoder:
    model.compile(optimizer='sgd', loss='mse')
    assert autoencoder.output_reconstruction

    model.fit(X_train, X_train, nb_epoch=1, batch_size=32)

    # predicting compressed representations of inputs:
    autoencoder.output_reconstruction = False  # the autoencoder has to be recompiled after modifying this property
    assert not autoencoder.output_reconstruction
    model.compile(optimizer='sgd', loss='mse')
    representations = model.predict(X_test)
    assert representations.shape == (100, 5)

    # the model is still trainable, although it now expects compressed representations as targets:
    model.fit(X_test, representations, nb_epoch=1, batch_size=32)

    # to keep training against the original inputs, just switch back output_reconstruction to True:
    autoencoder.output_reconstruction = True
    model.compile(optimizer='sgd', loss='mse')
    model.fit(X_train, X_train, nb_epoch=1)

    reconstructions = model.predict(X_test)
    assert reconstructions.shape == (100, 10)
Example #10
0
class QNetwork:
    def __init__(self, learning_rate=0.01, state_size=2, action_size=3, hidden_size=10):
        self.model = Sequential()
        self.model.add(Dense(hidden_size, activation='relu', input_dim=state_size))
        self.model.add(Dense(hidden_size, activation='relu'))
        self.model.add(Dense(action_size, activation='linear'))
        self.optimizer = Adam(lr=learning_rate)  # 誤差を減らす学習方法はAdam
        # self.model.compile(loss='mse', optimizer=self.optimizer)
        self.model.compile(loss=huberloss, optimizer=self.optimizer)

    # 重みの学習
    def replay(self, memory, batch_size, gamma, targetQN):
        inputs = np.zeros((batch_size, 2))
        targets = np.zeros((batch_size, 3))
        mini_batch = memory.sample(batch_size)

        for i, (state_b, action_b, reward_b, next_state_b) in enumerate(mini_batch):
            inputs[i:i + 1] = state_b
            target = reward_b

            if not (next_state_b == np.zeros(state_b.shape)).all(axis=1):
                # 価値計算(DDQNにも対応できるように、行動決定のQネットワークと価値観数のQネットワークは分離)
                retmainQs = self.model.predict(next_state_b)[0]
                next_action = np.argmax(retmainQs)  # 最大の報酬を返す行動を選択する
                target = reward_b + gamma * targetQN.model.predict(next_state_b)[0][next_action]

            targets[i] = self.model.predict(state_b)    # Qネットワークの出力
            targets[i][action_b] = target               # 教師信号

        # shiglayさんよりアドバイスいただき、for文の外へ修正しました
        self.model.fit(inputs, targets, epochs=1, verbose=0)  # epochsは訓練データの反復回数、verbose=0は表示なしの設定