我开发了一个keras模型并试图将我的数据融入模型中。这是model.fit的代码
def train(run_name, start_epoch, stop_epoch, img_w):
# Input Parameters
img_h = 64
words_per_epoch = 300
val_split = 0.2
val_words = int(words_per_epoch * (val_split))
# Network parameters
conv_filters = 16
kernel_size = (3, 3)
pool_size = 2
time_dense_size = 32
rnn_size = 256
minibatch_size = 32
if K.image_data_format() == 'channels_first':
input_shape = (1, img_w, img_h)
else:
input_shape = (img_w, img_h, 1)
act = 'relu'
input_data = Input(name='the_input', shape=input_shape, dtype='float32')
inner = Conv2D(conv_filters, kernel_size, padding='same',
activation=act, kernel_initializer='he_normal',
name='conv1')(input_data)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max1')(inner)
inner = Conv2D(conv_filters, kernel_size, padding='same',
activation=act, kernel_initializer='he_normal',
name='conv2')(inner)
inner = MaxPooling2D(pool_size=(pool_size, pool_size), name='max2')(inner)
conv_to_rnn_dims = (img_w // (pool_size ** 2), (img_h // (pool_size ** 2)) * conv_filters)
inner = Reshape(target_shape=conv_to_rnn_dims, name='reshape')(inner)
# cuts down input size going into RNN:
inner = Dense(time_dense_size, activation=act, name='dense1')(inner)
# Two layers of bidirectional GRUs
# GRU seems to work as well, if not better than LSTM:
gru_1 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru1')(inner)
gru_1b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru1_b')(inner)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(rnn_size, return_sequences=True, kernel_initializer='he_normal', name='gru2')(gru1_merged)
gru_2b = GRU(rnn_size, return_sequences=True, go_backwards=True, kernel_initializer='he_normal', name='gru2_b')(gru1_merged)
# transforms RNN output to character activations:
# print("Output Size",img_gen.get_output_size())
inner = Dense(47, kernel_initializer='he_normal',
name='dense2')(concatenate([gru_2, gru_2b]))
y_pred = Activation('softmax', name='softmax')(inner)
# Model(inputs=input_data, outputs=y_pred).summary()
labels = Input(name='the_labels', shape=[10], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
# Keras doesn't currently support loss funcs with extra parameters
# so CTC loss is implemented in a lambda layer
loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name='ctc')([y_pred, labels, input_length, label_length])
# clipnorm seems to speeds up convergence
sgd = SGD(lr=0.02, decay=1e-6, momentum=0.9, nesterov=True, clipnorm=5)
model = Model(inputs=[input_data, labels, input_length, label_length], outputs=loss_out)
# the loss calc occurs elsewhere, so use a dummy lambda func for the loss
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=sgd)
test_func = K.function([input_data], [y_pred])
# viz_cb = VizCallback(run_name, test_func, img_gen.next_val())
(X_train, y_train, train_input_length, train_labels_length), (X_test, y_test, test_input_length, test_labels_length) = dataset_load('./OCR_BanglaData.pkl.gz')
print(y_train[0])
X_train = X_train.reshape(X_train.shape[0], 128,64,1)
X_test = X_test.reshape(X_test.shape[0], 128,64,1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
model.fit((np.array(X_train), np.array(y_train),np.array(train_input_length), np.array(train_labels_length)), batch_size=32, epochs=120, verbose=1,validation_data=[np.array(X_test), np.array(y_test),np.array(test_input_length), np.array(test_labels_length)])
在此之后我收到此错误
TypeError: Error when checking model input: data should be a Numpy array, or list/dict of Numpy arrays.
我尝试打印每个数组的数据类型。结果是
<type 'numpy.ndarray'>
但我仍然收到此错误。它有什么具体原因吗? 我使用tensorflow模型作为我的keras后端。
答案 0 :(得分:0)
这里有4个输入:
model = Model(inputs=[input_data, labels, input_length, label_length], outputs=loss_out)
四个输入中的每一个都必须是一个numpy数组,fit方法需要它们在列表中(你使用的是元组):
model.fit([X_train, y_train,train_input_length, train_labels_length],...)
你错过了fit
方法中的输出。在创建模型时,某些内容必须与您定义为loss_out
的内容相匹配。