使用Tensorflow 2.0进行Logistic回归？

使用Tensorflow 2.0进行Logistic回归？

该模型未收敛，问题似乎出在您正在直接进行S型激活

tf.nn.softmax_cross_entropy_with_logits

。在文档中

tf.nn.softmax_cross_entropy_with_logits

说：

警告：该 *** 作程序期望未缩放的logit，因为它

softmax

在

logits

内部执行on来提高效率。请勿使用的输出调用此op

softmax

，因为它将产生不正确的结果。

因此，在传递给之前，不应在前一层的输出上执行softmax，Sigmoid，relu，tanh或任何其他激活 *** 作

tf.nn.softmax_cross_entropy_with_logits

。有关何时使用S形或softmax输出激活的更多详细说明，请参见此处。

因此，通过

return tf.nn.sigmoid(lr)

仅

returnlr

在

logistic_regression

函数中进行替换，模型正在收敛。

以下是具有上述修复功能的代码的有效示例。我还将变量名更改为

epochs

，

n_batches

因为您的训练循环实际上经历了1000个批次而不是1000个时期（我也将其提高到10000个，因为有迹象表明需要更多的迭代）。

from tensorflow.keras.datasets import fashion_mnistfrom sklearn.model_selection import train_test_splitimport tensorflow as tf(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()x_train, x_test = x_train/255., x_test/255.x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size=0.15)x_train = tf.reshape(x_train, shape=(-1, 784))x_test  = tf.reshape(x_test, shape=(-1, 784))weights = tf.Variable(tf.random.normal(shape=(784, 10), dtype=tf.float64))biases  = tf.Variable(tf.random.normal(shape=(10,), dtype=tf.float64))def logistic_regression(x):    lr = tf.add(tf.matmul(x, weights), biases)    #return tf.nn.sigmoid(lr)    return lrdef cross_entropy(y_true, y_pred):    y_true = tf.one_hot(y_true, 10)    loss = tf.nn.softmax_cross_entropy_with_logits(labels=y_true, logits=y_pred)    return tf.reduce_mean(loss)def accuracy(y_true, y_pred):    y_true = tf.cast(y_true, dtype=tf.int32)    preds = tf.cast(tf.argmax(y_pred, axis=1), dtype=tf.int32)    preds = tf.equal(y_true, preds)    return tf.reduce_mean(tf.cast(preds, dtype=tf.float32))def grad(x, y):    with tf.GradientTape() as tape:        y_pred = logistic_regression(x)        loss_val = cross_entropy(y, y_pred)    return tape.gradient(loss_val, [weights, biases])n_batches = 10000learning_rate = 0.01batch_size = 128dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))dataset = dataset.repeat().shuffle(x_train.shape[0]).batch(batch_size)optimizer = tf.optimizers.SGD(learning_rate)for batch_numb, (batch_xs, batch_ys) in enumerate(dataset.take(n_batches), 1):    gradients = grad(batch_xs, batch_ys)    optimizer.apply_gradients(zip(gradients, [weights, biases]))    y_pred = logistic_regression(batch_xs)    loss = cross_entropy(batch_ys, y_pred)    acc = accuracy(batch_ys, y_pred)    print("Batch number: %i, loss: %f, accuracy: %f" % (batch_numb, loss, acc))(removed printouts)>> Batch number: 1000, loss: 2.868473, accuracy: 0.546875(removed printouts)>> Batch number: 10000, loss: 1.482554, accuracy: 0.718750