Python tflearn.DNN属性代码示例

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def main(filename, frames, batch_size, num_classes, input_length):
    """From the blog post linked above."""
    # Get our data.
    X_train, _, y_train, _ = get_data(filename, frames, num_classes, input_length)

    # Get sizes.
    num_classes = len(y_train[0])

    # Get our network.
    net = get_network_wide(frames, input_length, num_classes)

    # Get our model.
    model = tflearn.DNN(net, tensorboard_verbose=0)
    model.load('checkpoints/rnn.tflearn')

    # Evaluate.
    print(model.evaluate(X_train, y_train)) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def main(filename, frames, batch_size, num_classes, input_length):
    """From the blog post linked above."""
    # Get our data.
    X_train, X_test, y_train, y_test = get_data(filename, frames, num_classes, input_length)

    # Get sizes.
    num_classes = len(y_train[0])

    # Get our network.
    net = get_network_wide(frames, input_length, num_classes)

    # Train the model.
    model = tflearn.DNN(net, tensorboard_verbose=0)
    model.fit(X_train, y_train, validation_set=(X_test, y_test),
              show_metric=True, batch_size=batch_size, snapshot_step=100,
              n_epoch=4)

    # Save it.
    model.save('checkpoints/rnn.tflearn') 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def resnext(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
    net = input_data(shape=[None, width, height, 3], name='input')
    net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
    net = tflearn.layers.conv.resnext_block(net, n, 16, 32)
    net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
    net = tflearn.resnext_block(net, n-1, 32, 32)
    net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
    net = tflearn.resnext_block(net, n-1, 64, 32)
    net = tflearn.batch_normalization(net)
    net = tflearn.activation(net, 'relu')
    net = tflearn.global_avg_pool(net)
    # Regression
    net = tflearn.fully_connected(net, output, activation='softmax')
    opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
    net = tflearn.regression(net, optimizer=opt,
                             loss='categorical_crossentropy')

    model = tflearn.DNN(net,
                        max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')

    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def build_network(self):
      print("---> Starting Neural Network") 
      self.network = input_data(shape = [None, 48, 48, 1])
      self.network = conv_2d(self.network, 64, 5, activation = 'relu')
      self.network = max_pool_2d(self.network, 3, strides = 2)
      self.network = conv_2d(self.network, 64, 5, activation = 'relu')
      self.network = max_pool_2d(self.network, 3, strides = 2)
      self.network = conv_2d(self.network, 128, 4, activation = 'relu')
      self.network = dropout(self.network, 0.3)
      self.network = fully_connected(self.network, 3072, activation = 'relu')
      self.network = fully_connected(self.network, len(self.target_classes), activation = 'softmax')
      self.network = regression(self.network,
        optimizer = 'momentum',
        loss = 'categorical_crossentropy')
      self.model = tflearn.DNN(
        self.network,
        checkpoint_path = 'model_1_nimish',
        max_checkpoints = 1,
        tensorboard_verbose = 2
      )
      self.load_model() 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def test_feed_dict_no_None(self):

        X = [[0., 0., 0., 0.], [1., 1., 1., 1.], [0., 0., 1., 0.], [1., 1., 1., 0.]]
        Y = [[1., 0.], [0., 1.], [1., 0.], [0., 1.]]

        with tf.Graph().as_default():
            g = tflearn.input_data(shape=[None, 4], name="X_in")
            g = tflearn.reshape(g, new_shape=[-1, 2, 2, 1])
            g = tflearn.conv_2d(g, 4, 2)
            g = tflearn.conv_2d(g, 4, 1)
            g = tflearn.max_pool_2d(g, 2)
            g = tflearn.fully_connected(g, 2, activation='softmax')
            g = tflearn.regression(g, optimizer='sgd', learning_rate=1.)

            m = tflearn.DNN(g)

            def do_fit():
                m.fit({"X_in": X, 'non_existent': X}, Y, n_epoch=30, snapshot_epoch=False)
            self.assertRaisesRegexp(Exception, "Feed dict asks for variable named 'non_existent' but no such variable is known to exist", do_fit) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def build_simple_model(self):
        """Build a simple model for test
        Returns:
            DNN, [ (input layer name, input placeholder, input data) ], Target data
        """
        inputPlaceholder1, inputPlaceholder2 = \
            tf.placeholder(tf.float32, (1, 1), name = "input1"), tf.placeholder(tf.float32, (1, 1), name = "input2")
        input1 = tflearn.input_data(placeholder = inputPlaceholder1)
        input2 = tflearn.input_data(placeholder = inputPlaceholder2)
        network = tflearn.merge([ input1, input2 ], "sum")
        network = tflearn.reshape(network, (1, 1))
        network = tflearn.fully_connected(network, 1)
        network = tflearn.regression(network)
        return (
            tflearn.DNN(network),
            [ ("input1:0", inputPlaceholder1, self.INPUT_DATA_1), ("input2:0", inputPlaceholder2, self.INPUT_DATA_2) ],
            self.TARGET,
        ) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def get_nn_model(checkpoint_path='nn_motor_model', session=None):
    # Input is a single value (raw motor value)
    network = input_data(shape=[None, 1], name='input')

    # Hidden layer no.1,  
    network = fully_connected(network, 12, activation='linear')
    
    # Output layer
    network = fully_connected(network, 1, activation='tanh')

    # regression
    network = regression(network, loss='mean_square', metric='accuracy', name='target')

    # Verbosity yay nay
    model = tflearn.DNN(network, tensorboard_verbose=3, checkpoint_path=checkpoint_path, session=session)
    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def createDNNLayers(self, x, y):

        ###############################################################
        #
        # Sets up the DNN layers, configuration in required/confs.json
        #
        ###############################################################
        
        net = tflearn.input_data(shape=[None, len(x[0])])

        for i in range(self._confs["NLU"]['FcLayers']):
            net = tflearn.fully_connected(net, self._confs["NLU"]['FcUnits'])

        net = tflearn.fully_connected(net, len(y[0]), activation=str(self._confs["NLU"]['Activation']))

        if self._confs["NLU"]['Regression']:
            net = tflearn.regression(net)

        return net 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def finalize_get_model(net, flags):
    net['gap'], curr = dup(global_avg_pool(net['conv_final'], name='gap'))

    net['final'] = regression(curr,
                              optimizer='adam',
                              learning_rate=flags.lr,
                              batch_size=flags.bs,
                              loss='softmax_categorical_crossentropy',
                              name='target',
                              n_classes=flags.nc,
                              shuffle_batches=True)

    model = tflearn.DNN(net['final'],
                        tensorboard_verbose=0,
                        tensorboard_dir=flags.logdir,
                        best_checkpoint_path=os.path.join(flags.logdir,
                                                          flags.run_id,
                                                          flags.run_id),
                        best_val_accuracy=flags.acc_save)

    model.net_dict = net
    model.flags = flags

    return model 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def test_case1():
    x = [1,2,3]
    y = [0.01,0.99]
    # 多组x作为输入样本
    X = np.array(np.repeat([x], 1, axis=0))
    # 多组y作为样本的y值
    Y = np.array(np.repeat([y], 1, axis=0))

    #X = np.array([x1,x2], dtype=np.float32)
    #Y = np.array([y1,y2])

    # 这里的第二个数对应了x是多少维的向量
    net = tflearn.input_data(shape=[None, 3])
    #net = tflearn.fully_connected(net, 32)
    net = tflearn.fully_connected(net, 2)
    # 这里的第二个参数对应了输出的y是多少维的向量
    #net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net)


    model = tflearn.DNN(net)
    model.fit(X, Y, n_epoch=1000, batch_size=1, show_metric=True, snapshot_epoch=False)
    pred = model.predict([x])
    print(pred) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def build_estimator(model_dir, model_type, embeddings,index_map, combination_method):
  """Build an estimator."""

  # Continuous base columns.
  node1 = tf.contrib.layers.real_valued_column("node1")

  deep_columns = [node1]
  
  if model_type == "regressor":
      
      tflearn.init_graph(num_cores=8, gpu_memory_fraction=0.5)
      if combination_method == 'concatenate':
          net = tflearn.input_data(shape=[None, embeddings.shape[1]*2])
      else:
        net = tflearn.input_data(shape=[None, embeddings.shape[1]] )
      net = tflearn.fully_connected(net, 100, activation='relu')
      net = tflearn.fully_connected(net, 2, activation='softmax')
      net = tflearn.regression(net, optimizer='adam', loss='categorical_crossentropy')
      m = tflearn.DNN(net)
  else:
    m = tf.contrib.learn.DNNLinearCombinedClassifier(
        model_dir=model_dir,
        linear_feature_columns=wide_columns,
        dnn_feature_columns=deep_columns,
        dnn_hidden_units=[100])
  return m 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def main(filename, frames, batch_size, num_classes, input_length):
    # Get our data.
    X, Y = get_data(input_data_dump, num_frames_per_video, labels, False)

    num_classes = len(labels)
    size_of_each_frame = X.shape[2]

    # Get our network.
    net = get_network_wide(num_frames_per_video, size_of_each_frame, num_classes)

    # Train the model.
    model = tflearn.DNN(net, tensorboard_verbose=0)
    try:
        model.load('checkpoints/' + model_file)
        print("\nModel Exists! Loading it")
        print("Model Loaded")
    except Exception:
        print("\nNo previous checkpoints of %s exist" % (model_file))
        print("Exiting..")
        sys.exit()

    predictions = model.predict(X)
    predictions = np.array([np.argmax(pred) for pred in predictions])
    Y = np.array([np.argmax(each) for each in Y])

    # Writing predictions and gold labels to file
    rev_labels = dict(zip(list(labels.values()), list(labels.keys())))
    print(rev_labels)
    with open("result.txt", "w") as f:
        f.write("gold, pred\n")
        for a, b in zip(Y, predictions):
            f.write("%s %s\n" % (rev_labels[a], rev_labels[b]))

    acc = 100 * np.sum(predictions == Y) / len(Y)
    print("Accuracy: ", acc) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def main(input_data_dump, num_frames_per_video, batch_size, labels, model_file):
    # Get our data.
    X_train, X_test, y_train, y_test = get_data(input_data_dump, num_frames_per_video, labels, True)

    num_classes = len(labels)
    size_of_each_frame = X_train.shape[2]

    # Get our network.
    net = get_network_wide(num_frames_per_video, size_of_each_frame, num_classes)

    # Train the model.
    try:
        model = tflearn.DNN(net, tensorboard_verbose=0)
        model.load('checkpoints/' + model_file)
        print("\nModel already exists! Loading it")
        print("Model Loaded")
    except Exception:
        model = tflearn.DNN(net, tensorboard_verbose=0)
        print("\nNo previous checkpoints of %s exist" % (model_file))

    model.fit(X_train, y_train, validation_set=(X_test, y_test),
              show_metric=True, batch_size=batch_size, snapshot_step=100,
              n_epoch=10)

    # Save it.
    x = input("Do you wanna save the model and overwrite? y or n: ")
    if(x.strip().lower() == "y"):
        model.save('checkpoints/' + model_file) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def vgg_net_19(width, height):
    network = input_data(shape=[None, height, width, 3], name='input')
    network = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 1000, activation='softmax', weight_decay=5e-4)
    
    opt = Momentum(learning_rate=0, momentum = 0.9)
    network = regression(network, optimizer=opt, loss='categorical_crossentropy', name='targets')
    
    model = DNN(network, checkpoint_path='', max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='')
    
    return model

#model of vgg-19 for testing of the activations 
#rename the output you want to test, connect it to the next layer and change the output layer at the bottom (model = DNN(...))
#make sure to use the correct test function (depending if your output is a tensor or a vector) 

# 需要导入模块: import tflearn [as 别名]
# 或者: from tflearn import DNN [as 别名]
def vgg_net_19_activations(width, height):
    network = input_data(shape=[None, height, width, 3], name='input')
    network1 = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network2 = conv_2d(network1, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network2, 2, strides=2)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
    network = max_pool_2d(network, 2, strides=2)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
    network = dropout(network, keep_prob=0.5)
    network = fully_connected(network, 1000, activation='softmax', weight_decay=5e-4)
    
    opt = Momentum(learning_rate=0, momentum = 0.9)
    network = regression(network, optimizer=opt, loss='categorical_crossentropy', name='targets')
    
    model = DNN(network1, checkpoint_path='', max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='')
    
    return model