tf.nn.sampled_softmax_loss用法详解

tensorflow中具体的函数说明如下：

tf.nn.sampled_softmax_loss(weights, # Shape (num_classes, dim)     - floatXX
                     biases,        # Shape (num_classes)          - floatXX 
                     labels,        # Shape (batch_size, num_true) - int64
                     inputs,        # Shape (batch_size, dim)      - floatXX  
                     num_sampled,   # - int
                     num_classes,   # - int
                     num_true=1,  
                     sampled_values=None,
                     remove_accidental_hits=True,
                     partition_strategy="mod",
                     name="sampled_softmax_loss")

使用样例

import tensorflow as tf

# Network Parameters
n_hidden_1 = 256  # 1st layer number of features
n_input = 784     # MNIST data input (img shape: 28*28)
n_classes = 10    # MNIST total classes (0-9 digits)

# Dependent & Independent Variable Placeholders
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes]) #

# Weights and Biases
weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'out': tf.Variable(tf.random_normal([n_hidden_1, n_classes]))
}
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

# Super simple model builder
def tiny_perceptron(x, weights, biases):
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    out_layer = tf.nn.relu(layer_1)
    # out_layer = tf.matmul(layer_1, weights['out']) + biases['out']
    return out_layer

# Create the model
pred = tiny_perceptron(x, weights, biases)

# Set up loss function inputs and inspect their shapes
w = tf.transpose(weights['out'])
b = biases['out']
labels = tf.reshape(tf.argmax(y, 1), [-1,1])
inputs = pred
num_sampled = 3
num_true = 1
num_classes = n_classes

print('Shapes\n------\nw:\t%s\nb:\t%s\nlabels:\t%s\ninputs:\t%s' % (w.shape, b.shape, labels.shape, inputs.shape))
# Shapes
# ------
# w:      (10, 256)  # Requires (num_classes, dim)     - CORRECT
# b:      (10,)      # Requires (num_classes)          - CORRECT
# labels: (?, 1)     # Requires (batch_size, num_true) - CORRECT
# inputs: (?, 256)    # Requires (batch_size, dim)     - CORRECT

loss_function = tf.reduce_mean(tf.nn.sampled_softmax_loss(
                     weights=w,
                     biases=b,
                     labels=labels,
                     inputs=inputs,
                     num_sampled=num_sampled,
                     num_true=num_true,
                     num_classes=num_classes)
)

需要提到的是，这里的labels如果是one-hot类型编码，需要labels=tf.reshape(tf.argmax(labels_one_hot, 1), [-1,1])

参考地址：https://stackoverflow.com/questions/43810195/tensorflow-sampled-softmax-loss-correct-usage