我想使用Bert训练 21类文本分类模型。但是我的训练数据很少,因此下载了一个具有 5个班级的类似数据集,其中包含200万个样本。
并使用bert提供的无条件预训练模型微调下载的数据。
并获得了约98%的验证准确性。
现在,我想将此模型用作我的小型自定义数据的预训练模型。
但是我收到shape mismatch with tensor output_bias from checkpoint reader
错误,因为检查点模型有5个类,而我的自定义数据有21个类。
NFO:tensorflow:Calling model_fn.
INFO:tensorflow:Running train on CPU
INFO:tensorflow:*** Features ***
INFO:tensorflow: name = input_ids, shape = (32, 128)
INFO:tensorflow: name = input_mask, shape = (32, 128)
INFO:tensorflow: name = is_real_example, shape = (32,)
INFO:tensorflow: name = label_ids, shape = (32, 21)
INFO:tensorflow: name = segment_ids, shape = (32, 128)
Tensor("IteratorGetNext:3", shape=(32, 21), dtype=int32)
WARNING:tensorflow:From /home/user/Spine_NLP/bert/modeling.py:358: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
WARNING:tensorflow:From /home/user/Spine_NLP/bert/modeling.py:671: dense (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dense instead.
INFO:tensorflow:num_labels:21;logits:Tensor("loss/BiasAdd:0", shape=(32, 21), dtype=float32);labels:Tensor("loss/Cast:0", shape=(32, 21), dtype=float32)
INFO:tensorflow:Error recorded from training_loop: Shape of variable output_bias:0 ((21,)) doesn't match with shape of tensor output_bias ([5]) from checkpoint reader.
答案 0 :(得分:3)
如果您想使用5个类的预训练模型对自己的模型进行微调,则可能需要添加一层,以将5个类投影到21个类中。
>您看到的错误是由于您可能未定义一组新的“ output_weights”和“ output_bias”,而是将它们重新用于21个类的新标签。下面,我用“ final_”为新标签“中间”前缀中间张量。
代码应类似于以下内容:
# These are the logits for the 5 classes. Keep them as is.
logits = tf.matmul(output_layer, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
# You want to create one more layer
final_output_weights = tf.get_variable(
"final_output_weights", [21, 5],
initializer=tf.truncated_normal_initializer(stddev=0.02))
final_output_bias = tf.get_variable(
"final_output_bias", [21], initializer=tf.zeros_initializer())
final_logits = tf.matmul(logits, final_output_weights, transpose_b=True)
final_logits = tf.nn.bias_add(final_logits, final_output_bias)
# Below is for evaluating the classification.
final_probabilities = tf.nn.softmax(final_logits, axis=-1)
final_log_probs = tf.nn.log_softmax(final_logits, axis=-1)
# Note labels below should be the 21 class ids.
final_one_hot_labels = tf.one_hot(labels, depth=21, dtype=tf.float32)
final_per_example_loss = -tf.reduce_sum(final_one_hot_labels * final_log_probs, axis=-1)
final_loss = tf.reduce_mean(final_per_example_loss)