是否可能有一个具有多个输出的回归模型？

Question

我正在使用 Tensorflow 处理 CNN 回归模型。我想知道是否可以使用回归从我的数据集中估计多个数据？（换句话说，我想用头和双手的位置和旋转来估计人体肩膀和肘部的位置（x，y，z）和旋转（俯仰，偏航，滚动））

所以，我的模型的输出应该是每个关节的 6 个值。（例如：肘部）这也是我的代码示例：（我使用 tf.session 来训练模型）

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 42], name ='input_node')
ys = tf.placeholder(tf.float32, [None, 1]) 
keep_prob = tf.placeholder(tf.float32) 

#Network computations and Layers
x_image = tf.reshape(xs, [-1, 3, 3,1])  
## conv1 layer
W_conv1 = weight_func([3, 3, 1, 32])  
b_conv1 = bias_func([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) 
h_pool1 = max_pool_2x2(h_conv1)     
# h_drop1 = tf.nn.dropout(h_conv1, keep_prob) 

## conv2 layer
W_conv2 = weight_func([3, 3, 32, 64])
b_conv2 = bias_func([64])
h_conv2 = tf.nn.relu(conv2d(h_conv1, W_conv2) + b_conv2)
# h_drop2 = tf.nn.dropout(h_conv2, keep_prob)

## conv3 layer
W_conv3 = weight_func([3, 3, 64, 128])  
b_conv3 = bias_func([128])
h_conv3 = tf.nn.relu(conv2d(h_conv2, W_conv3) + b_conv3)  
# h_drop3 = tf.nn.dropout(h_conv3, keep_prob)  

## conv4 layer 
W_conv4 = weight_func([3, 3, 128,256]) 
b_conv4 = bias_func([256])
h_conv4 = tf.nn.relu(conv2d(h_conv3, W_conv4) + b_conv4) 
# h_drop4 = tf.nn.dropout(h_conv4, keep_prob)  

## fc1 layer 
W_fc1 = weight_func([3 * 3 * 256, 2304])
b_fc1 = bias_func([256])

h_pool2_flat = tf.reshape(h_conv4, [-1, 3* 3 * 256]) 
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) 

# fc2 layer ## full connection
W_fc2 = weight_func([2304, 1])
b_fc2 = bias_func([1])

prediction = tf.add(tf.matmul(h_fc1_drop, W_fc2) , b_fc2, name= 'output_node')
cross_entropy = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))

sess = tf.Session()
train_step = tf.train.AdamOptimizer(0.01).minimize(cross_entropy)
sess.run(tf.global_variables_initializer())
init=tf.global_variables_initializer()
for i in range(50):
  sess.run([train_step] , feed_dict = {xs: train_x, ys: train_y, keep_prob: 0.7})
prediction_value = sess.run(prediction, feed_dict={xs: test_x, ys: test_y, keep_prob: 1.0})`

Answer 1

当然可以，只需创建第二个输出即可。不幸的是，我无法告诉您如何为 Tensorflow 1.14 执行此操作，但在 TF2.0 中就像我在另一个模型中所做的那样：

output_categorical = layer.Dense(5, activation="softmax")(dense_layer_out_cat)
output_continuus = layer.Dense(1, activation="sigmoid")(dense_layer_out_con)
model = tf.keras.Model(inputs=[layer_input_categorical, layer_input_categorical_2, layer_input_continuus], \
                       outputs=[output_categorical, output_continuus])
model.compile(optimizer="Nadam", loss=["mse","sparse_categorical_crossentropy"])

在这段代码中您可以看到一个模型，输出一个回归值和一个分类值（用于分类）。最后就是这样，没有什么大魔法。只需创建两个带有 sigmoid 激活的输出层，告诉模型将两个层都用作输出，定义 two！损失函数（可能是相同的 6 次，如果你进行 6 次回归）就是这样。拥有多个输出也意味着，您当然需要与输出一样多的 y-label 值，因此在数据准备过程中请记住这一点。

是否可能有一个具有多个输出的回归模型？

is it possible to have a regression model with more than one output?

estimation

regression

orientation

supervised-learning

tensorflow