堆栈内存溢出
  简体   繁体   English

CNN 回归 model 对所有输入给出类似的 output

[英]CNN regression model gives similar output for all inputs

 原文  2021-02-13 07:17:12  8   2    tensorflow/ deep-learning/ neural-network/ regression/ conv-neural-network

问题描述

I'm trying to build a CNN regression model. The input data is satellite images of 5 (256x256x5) bands over 10 years stacked together to obtain an array of 256x256x50.我正在尝试构建 CNN 回归 model。输入数据是 5 (256x256x5) 个波段 10 年以上的卫星图像叠加在一起以获得 256x256x50 的数组。

channels=50
l2(0.0005)
model = models.Sequential()
input_shape=(img_size,img_size,channels)
chanDim=1
reg=l2(0.0005)
init='he_normal'
model.add(layers.Conv2D(64, (7, 7),strides=(2,2),padding='valid',
                        kernel_initializer=init,
                        kernel_regularizer=reg, input_shape=input_shape))
model.add(layers.Activation('gelu'))
model.add(layers.BatchNormalization(axis=chanDim))

model.add(layers.Conv2D(32, (3, 3),padding='valid',
                        kernel_initializer=init,
                        kernel_regularizer=reg))
model.add(layers.Activation('gelu'))
model.add(layers.BatchNormalization(axis=chanDim))

model.add(layers.Conv2D(64, (3, 3),padding='valid',
                        kernel_initializer=init,
                        kernel_regularizer=reg))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization(axis=chanDim))
model.add(layers.Dropout(0.25))

model.add(layers.Conv2D(64, (3, 3),padding='valid',
                        kernel_initializer=init,
                        kernel_regularizer=reg))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization(axis=chanDim))
model.add(layers.Conv2D(128, (3, 3),padding='valid',
                        kernel_initializer=init,
                        kernel_regularizer=reg))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization(axis=chanDim))
model.add(layers.Dropout(0.25))

model.add(layers.Conv2D(128, (3, 3),padding='valid',
                        kernel_initializer=init,
                        kernel_regularizer=reg))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization(axis=chanDim))

# model.add(layers.Conv2D(512, (3, 3),padding='valid',
#                         kernel_initializer=init,
#                         kernel_regularizer=reg))
# model.add(layers.Activation('relu'))
# model.add(layers.BatchNormalization(axis=chanDim))
# model.add(layers.Dropout(0.25))

model.add(layers.Flatten())
model.add(layers.Dense(128, activation='gelu'))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(32, activation='relu'))
model.add(layers.Dropout(.5))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='relu'))
model.compile(optimizer=tf.keras.optimizers.Adam(lr=1e-7), loss='mae')

Training steps:训练步骤：

Epoch 1/30
8/8 [==============================] - 208s 26s/step - loss: 1.3836 - val_loss: 1.3476
Epoch 2/30
8/8 [==============================] - 81s 11s/step - loss: 1.3826 - val_loss: 1.3476
Epoch 3/30
8/8 [==============================] - 61s 8s/step - loss: 1.3863 - val_loss: 1.3476
Epoch 4/30
8/8 [==============================] - 60s 8s/step - loss: 1.3837 - val_loss: 1.3476
Epoch 5/30
8/8 [==============================] - 61s 8s/step - loss: 1.3785 - val_loss: 1.3476
Epoch 6/30
8/8 [==============================] - 60s 8s/step - loss: 1.3863 - val_loss: 1.3476
Epoch 7/30
8/8 [==============================] - 60s 8s/step - loss: 1.3869 - val_loss: 1.3476
Epoch 8/30
8/8 [==============================] - 60s 8s/step - loss: 1.3665 - val_loss: 1.3476
Epoch 9/30
8/8 [==============================] - 60s 8s/step - loss: 1.3060 - val_loss: 1.3476
Epoch 10/30
8/8 [==============================] - 61s 8s/step - loss: 1.2391 - val_loss: 1.3443
Epoch 11/30
8/8 [==============================] - 60s 8s/step - loss: 1.1757 - val_loss: 1.2622
Epoch 12/30
8/8 [==============================] - 61s 8s/step - loss: 1.1277 - val_loss: 1.1432
Epoch 13/30
8/8 [==============================] - 60s 8s/step - loss: 1.0967 - val_loss: 1.0280
Epoch 14/30
8/8 [==============================] - 60s 8s/step - loss: 1.0408 - val_loss: 0.9306
Epoch 15/30
8/8 [==============================] - 61s 8s/step - loss: 1.0423 - val_loss: 0.8529
Epoch 16/30
8/8 [==============================] - 60s 8s/step - loss: 1.0277 - val_loss: 0.7910
Epoch 17/30
8/8 [==============================] - 61s 8s/step - loss: 1.0800 - val_loss: 0.7385
Epoch 18/30
8/8 [==============================] - 61s 8s/step - loss: 0.9982 - val_loss: 0.6957
Epoch 19/30
8/8 [==============================] - 62s 8s/step - loss: 1.0466 - val_loss: 0.6648
Epoch 20/30
8/8 [==============================] - 61s 8s/step - loss: 1.0755 - val_loss: 0.6431
Epoch 21/30
8/8 [==============================] - 61s 8s/step - loss: 0.9773 - val_loss: 0.6270
Epoch 22/30
8/8 [==============================] - 61s 8s/step - loss: 0.9878 - val_loss: 0.6173
Epoch 23/30
8/8 [==============================] - 62s 8s/step - loss: 0.9546 - val_loss: 0.6107
Epoch 24/30
8/8 [==============================] - 62s 8s/step - loss: 0.9736 - val_loss: 0.6066
Epoch 25/30
8/8 [==============================] - 62s 8s/step - loss: 0.9398 - val_loss: 0.6051
Epoch 26/30
8/8 [==============================] - 61s 8s/step - loss: 0.9513 - val_loss: 0.6064
Epoch 27/30
8/8 [==============================] - 61s 8s/step - loss: 0.9850 - val_loss: 0.6085
Epoch 28/30
8/8 [==============================] - 61s 8s/step - loss: 0.9534 - val_loss: 0.6120
<tensorflow.python.keras.callbacks.History at 0x7f7e8049b630>

But predictions[:10] and expected_values[:10] are:但是 predictions[:10] 和 expected_values[:10] 是：

[[0.75141275][0.9683605 ][1.0075892 ][0.9710504 ][1.0537224 ][0.95761603]
 [0.8781187 ][0.9666001 ][1.0071822 ][0.8568193 ]]

 [0.96850154 0.98255504 0.88197998 0.7692161  0.9462668  0.81489973
 0.99938562 0.93442511 0.98891429 0.97386952]

Evalution scores are:评价分数为：

  • mean_absolute_error: 0.09588701954343189平均绝对误差：0.09588701954343189
  • mean_squared_error: 0.12396534977645424 mean_squared_error：0.12396534977645424
  • explained_variance_score: -0.4386057129990675 explained_variance_score：-0.4386057129990675
  • r2_score: -0.6250618533611494 r2_score：-0.6250618533611494

actual vs prediction plot实际与预测 plot

Any ideas?有任何想法吗？

2 个解决方案

解决方案1
 2 已采纳  2021-02-24 06:14:48

Someone suggested me to treat this time series data as video hence using Conv3D instead of Conv2D to solve this issue and it works, the model is now not predicting the same output.有人建议我将此时间序列数据视为视频，因此使用 Conv3D 而不是 Conv2D 来解决此问题并且它有效，model 现在无法预测相同的 output。 So, the input data should be in the shape [10, 256,256, 10] which represents [Year, Image shape, Image Shape, Channels/Bands] for the time-series input data因此，输入数据的形状应为[10, 256,256, 10] ，表示时间序列输入数据的[Year, Image shape, Image Shape, Channels/Bands]

解决方案2
 0  2021-08-25 13:32:54

It could also be that the problem is very hard to learn.也可能是这个问题很难学习。 I've had this and actually after 6 hours of identical outputs in each batch (which happens because the 'average' answer is the easiest to minimize loss), the.network finally started learning:我已经有了这个，实际上在每批输出相同的 6 小时之后（这是因为“平均”答案最容易减少损失），the.network 终于开始学习：

在此处输入图像描述

Some things I plan on doing to make the learning happen earlier:为了让学习更早发生，我计划做一些事情：

  1. changes in learning rate学习率的变化
  2. using features from earlier in the.network使用 .network 早期的功能

暂无
暂无

声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 Keras model 为所有输入提供相同的 output - Keras model gives same output for all inputs 如何训练 CNN 回归 model，它采用多个输入图像并给出单个值 output。 - How to train a CNN regression model, which takes multiple input images and gives a single value as output.? CNN model 预测任何输入的相同 output - CNN model predicting the same output for any inputs 模型为所有输入（keras）给出相同的输出，精度，损耗 - Model gives same output, accuracy, loss for all inputs (keras) CNN对所有输入形成相同的输出 - CNN forming same output for all inputs CNN 模型中的多个输入 - Multiple inputs in a CNN model 将 CNN 分类器 model 更改为 CNN 回归 model - Change a CNN classifier model to a CNN regression model 使用输入之一最小化 Tensorflow 回归 model 的 output - Minimize the output of Tensorflow regression model using one of the inputs 将多个输入传递给CNN模型 - Passing multiple inputs to CNN model Tensorflow 上带有回归输出的 CNN 图像识别 - CNN Image Recognition with Regression Output on Tensorflow
相关标签
 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM