Machine learning Keras目标尺寸不匹配
尝试使用Machine learning Keras目标尺寸不匹配,machine-learning,keras,neural-network,deep-learning,conv-neural-network,Machine Learning,Keras,Neural Network,Deep Learning,Conv Neural Network,尝试使用num\u classes=73解决单个标签分类问题 以下是我的简化Keras模型: num_classes = 73 batch_size = 4 train_data_list = [training_file_names list here..] validation_data_list = [ validation_file_names list here..] training_generator = DataGenerator(train_data_list, batch
num\u classes=73解决单个标签分类问题
以下是我的简化Keras模型:
num_classes = 73
batch_size = 4
train_data_list = [training_file_names list here..]
validation_data_list = [ validation_file_names list here..]
training_generator = DataGenerator(train_data_list, batch_size, num_classes)
validation_generator = DataGenerator(validation_data_list, batch_size, num_classes)
model = Sequential()
model.add(Conv1D(32, 3, strides=1, input_shape=(15,120), activation="relu"))
model.add(Conv1D(16, 3, strides=1, activation="relu"))
model.add(Flatten())
model.add(Dense(n_classes, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss="categorical_crossentropy",optimizer=sgd,metrics=['accuracy'])
model.fit_generator(generator=training_generator, epochs=100,
validation_data=validation_generator)
这是我的数据生成器
的\uu获取项目
方法:
def __get_item__(self):
X = np.zeros((self.batch_size,15,120))
y = np.zeros((self.batch_size, 1 ,self.n_classes))
for i in range(self.batch_size):
X_row = some_method_that_gives_X_of_15x20_dim()
target = some_method_that_gives_target()
one_hot = keras.utils.to_categorical(target, num_classes=self.n_classes)
X[i] = X_row
y[i] = one_hot
return X, y
由于我的X
值与维度(批次大小,15,120)
一起正确返回,因此我不在这里显示它。我的问题是返回的y值
从这个生成器方法返回的y
有一个(batch\u size,1,73)
的形状,作为73个类的一个热编码标签,我认为这是返回的正确形状
但是,对于最后一层,Keras给出了以下错误:
ValueError:检查目标时出错:预期密集_1有2个
维度,但获得了具有形状的数组(4,1,73)
由于批大小是4,我认为目标批也应该是三维的(4,1,73)。那么,为什么Keras希望最后一层是二维的呢?您的模型的摘要显示,在输出层中应该只有二维(无,73)
由于目标的维度是(batch_size,1,73),所以您只需更改为(batch_size,73)即可运行模型
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d_7 (Conv1D) (None, 13, 32) 11552
_________________________________________________________________
conv1d_8 (Conv1D) (None, 11, 16) 1552
_________________________________________________________________
flatten_5 (Flatten) (None, 176) 0
_________________________________________________________________
dense_4 (Dense) (None, 73) 12921
=================================================================
Total params: 26,025
Trainable params: 26,025
Non-trainable params: 0
_________________________________________________________________