当我在笔记本电脑上训练时,即使它在3个时期之后崩溃,但损失似乎正在减少。然而,当我转移到具有48个核心的集群时,在第一个时期之后的每个时期的损失都是纳米。对于第一个时期,损失是正常值,即40.9451
这是我的模特
model = Sequential()
model.add(Conv2D(64, (3, 3), activation='relu', input_shape=(241, 480, 7)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'))
model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same'))
model.add(Flatten())
model.add(Dense(256, activation='relu', kernel_initializer='glorot_normal'))
model.add(Dropout(0.5))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dense(1, activation='linear'))