python - 为什么 tape.gradient 在我的 Sequential 模型中不返回所有内容？

Question

我必须计算这个模型的梯度：

model=Sequential()
model.add(Dense(40, activation='relu',input_dim=12))
model.add(Dense(60, activation='relu'))
model.add(Dense(units=3, activation='softmax'))
opt=tf.keras.optimizers.Adam(lr=0.001)
model.compile(loss="mse", optimizer=opt)

model_q=Sequential()
model_q.add(Dense(40, activation='relu',input_dim=15))
model_q.add(Dense(60, activation='relu'))
model_q.add(Dense(units=1, activation='linear'))
opt=tf.keras.optimizers.Adam(lr=0.001)
model_q.compile(loss="mse", optimizer=opt)

x=np.random.random(12)
x2=model.predict(x.reshape(-1,12))
with tf.GradientTape() as tape:
            value = model_q([tf.convert_to_tensor(np.append(x,x2).reshape(-1,15))])
            loss = -tf.reduce_mean(value)
grad = tape.gradient(loss, model.trainable_variables)
opt.apply_gradients(zip(grad, model.trainable_variables))

但 grad 全部返回 none，因此 opt 无法将渐变应用于模型。为什么会这样？我知道这是一个很奇怪的损失，但这是我想计算的

标签： pythontensorflowgradientsequential

Answer 1

你model没有被磁带记录下来。如果要获得渐变，则必须将计算放入磁带的上下文中。

model=Sequential()
model.add(Dense(40, activation='relu',input_dim=12))
model.add(Dense(60, activation='relu'))
model.add(Dense(units=3, activation='softmax'))
opt=tf.keras.optimizers.Adam(lr=0.001)

model_q=Sequential()
model_q.add(Dense(40, activation='relu',input_dim=15))
model_q.add(Dense(60, activation='relu'))
model_q.add(Dense(units=1, activation='linear'))
opt=tf.keras.optimizers.Adam(lr=0.001)

x=np.random.random(12).reshape(-1,12)
with tf.GradientTape() as tape:
  x2 = model([x])
  value = model_q([tf.concat((x,x2), -1)])
  loss = -tf.reduce_mean(value)
grad = tape.gradient(loss, model.trainable_variables)
opt.apply_gradients(zip(grad, model.trainable_variables))