GNN解决图着色问题

Question

在tensorflow框架下，模型为GNN模型，要解决图着色（图论）问题，中间大致过程经过编码输入，RNN循环，聚合更新节点，颜色的嵌入，经固定次数嵌入更新，得到最后的节点和颜色的特征，输入MLP，进行预测任务：该图是否接受C中颜色着色？(二分类问题)
我想在最后一层激活函数sigmoid之前加入BN层，部分段代码如下：

    # Get the last embeddings
    last_states = gnn(
      { "M": M_matrix, "VC": VC_matrix, 'chrom_number': chrom_number },
      { "V": vertex_initial_embeddings, "C": colors_initial_embeddings },
      time_steps = time_steps
    )
    GNN["last_states"] = last_states
    V_n = last_states['V'].h
    C_n = last_states['C'].h
    # Compute a vote for each embedding
    V_vote = tf.reshape(V_vote_MLP(V_n), [-1])
    # Add Batch Normalization layer before activation function
    V_vote = tf.keras.layers.BatchNormalization()(V_vote)

    # Compute the number of problems in the batch
    num_problems = tf.shape(n_vertices)[0]
    pred_logits = tf.while_loop(
        lambda i, pred_logits: tf.less(i, num_problems),
        lambda i, pred_logits:
        (
            (i + 1),
            pred_logits.write(
                i,
                tf.reduce_mean(V_vote[tf.reduce_sum(n_vertices[0:i]):tf.reduce_sum(n_vertices[0:i]) + n_vertices[i]])
            )
        ),
        [0, tf.TensorArray(size=num_problems, dtype=tf.float32)]
    )[1].stack()

    # Add sigmoid activation function
    pred_logits = tf.keras.activations.sigmoid(pred_logits)

    # Assign predictions to dictionary
    GNN['predictions'] = pred_logits

出现了如下报错：ValueError: ('Input has undefined axis dimension. Input shape: ', TensorShape([None]))
我应该怎么修改代码呢？
同时我想在如下代码添加梯度裁剪该怎么添加呢？

 # Define loss
    GNN['loss'] = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=cn_exists, logits=pred_logits))

    # Define optimizer
    optimizer = tf.train.AdamOptimizer(name='Adam', learning_rate=learning_rate)

    # Compute cost relative to L2 normalization
    vars_cost = tf.add_n([ tf.nn.l2_loss(var) for var in tf.trainable_variables() ])

    # Define gradients and train step
    grads, _ = tf.clip_by_global_norm(tf.gradients(GNN['loss'] + tf.multiply(vars_cost, l2norm_scaling),tf.trainable_variables()),global_norm_gradient_clipping_ratio)
    GNN['train_step'] = optimizer.apply_gradients(zip(grads, tf.trainable_variables()))
    
    GNN['C_n'] = C_n

Answer 1

要在这段代码中添加梯度裁剪，您需要将 grads 张量传递到 tf.clip_by_global_norm() 函数中，并使用 global_norm_gradient_clipping_ratio 参数指定裁剪比率，例如：

```python
# Define gradients and train step with gradient clipping
grads, _ = tf.clip_by_global_norm(
    tf.gradients(
        GNN['loss'] + tf.multiply(vars_cost, l2norm_scaling),
        tf.trainable_variables()
    ),
    global_norm_gradient_clipping_ratio
)
GNN['train_step'] = optimizer.apply_gradients(zip(grads, tf.trainable_variables()))

```