各位好，最近剛接觸，還不是很清楚，問題很奇怪的話請見諒 (ง๑ •̀_•́)ง

我使用 keras 裡的數據來練習

可是發現我的 loss 不知道為什麼維持不變，看不出來哪裡怪怪的

從 epoch 1 開始就沒再改變過了

請問要怎麼修改才會比較正常?

謝謝

output

my_model.py

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import datasets

# x: (60000, 28, 28)
# y: (60000,)
(x, y), _ = tf.keras.datasets.mnist.load_data()

# 轉換成 tensor
x = tf.convert_to_tensor(x, dtype=tf.float32)/255   # 讓值範圍在 0 ~ 1
y = tf.convert_to_tensor(y, dtype=tf.int32)
 
train_db = tf.data.Dataset.from_tensor_slices((x, y)).batch(128)

# [b, 784] -> [b, 256] -> [b, 128] -> [b, 10] 
w1 = tf.Variable(tf.random.truncated_normal([784, 256], stddev=0.1))
b1 = tf.Variable(tf.zeros([256]))
w2 = tf.Variable(tf.random.truncated_normal([256, 128], stddev=0.1))
b2 = tf.Variable(tf.zeros([128]))
w3 = tf.Variable(tf.random.truncated_normal([128, 10], stddev=0.1))
b3 = tf.Variable(tf.zeros([10]))

lr = 1e-3

for epoch in range(10):
    print('---', epoch, '---')
    for step, (x, y) in enumerate(train_db):
        # x [128, 28, 28]
        # y [128]
        x = tf.reshape(x, [-1, 28*28])  # [128, 784]
        
        with tf.GradientTape() as tape: # tf.variable
            h1 = x@w1+b1
            h1 = tf.nn.relu(h1)
            h2 = h1@w2+b2
            h2 = tf.nn.relu(h2)
            y_out = h2@w3+b3

            # compute loss
            y_onehot = tf.one_hot(y, depth=10)
            loss = tf.reduce_mean(tf.square(y_onehot-y_out))

        # compute gradient
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])

        # update 
        w1.assign_sub(w1 - lr*grads[0]) 
        b1.assign_sub(b1 - lr*grads[1]) 
        w2.assign_sub(w2 - lr*grads[2]) 
        b2.assign_sub(b2 - lr*grads[3]) 
        w3.assign_sub(w3 - lr*grads[4]) 
        b3.assign_sub(b3 - lr*grads[5]) 

        if step%100 == 0:
            print(step, '\tloss:\t', float(loss))