带有变压器的分类模型的keras模型错误

Question

我遵循了这个教程： https://keras.io/examples/timeseries/timeseries_transformer_classification/ 对于带有变压器的分类模型到我的时间序列。但是，在行中：

x = layers.MultiHeadAttention(
            key_dim=head_size, num_heads=num_heads, dropout=dropout
        )(x, x)

我收到错误：

{IndexError}tuple index out of range

知道为什么吗？

Answer 1

披露：我来这里是为了赏金，然后我尝试了 Colab，一切正常..

接下来我阅读了评论：“这个问题在当前状态下是一个笑话。无法重现它。”在这一点上我同意。但由于我是 Hans in Luck 并且显然有很多时间拖延，所以我开始 Pycharm 按照 OP 提示：“不，当我粘贴它时我的 pycharm 我得到了上面的错误 "

但这对我也有效，这让我想知道你是否触及了什么，所以我很乐意为你提供一个（n）（未触及的）工作版本..

import numpy as np

def readucr(filename):
    data = np.loadtxt(filename, delimiter="\t")
    y = data[:, 0]
    x = data[:, 1:]
    return x, y.astype(int)


root_url = "https://raw.githubusercontent.com/hfawaz/cd-diagram/master/FordA/"

x_train, y_train = readucr(root_url + "FordA_TRAIN.tsv")
x_test, y_test = readucr(root_url + "FordA_TEST.tsv")

x_train = x_train.reshape((x_train.shape[0], x_train.shape[1], 1))
x_test = x_test.reshape((x_test.shape[0], x_test.shape[1], 1))

n_classes = len(np.unique(y_train))

idx = np.random.permutation(len(x_train))
x_train = x_train[idx]
y_train = y_train[idx]

y_train[y_train == -1] = 0
y_test[y_test == -1] = 0


from tensorflow import keras
from tensorflow.keras import layers

def transformer_encoder(inputs, head_size, num_heads, ff_dim, dropout=0):
    # Normalization and Attention
    x = layers.LayerNormalization(epsilon=1e-6)(inputs)
    x = layers.MultiHeadAttention(
        key_dim=head_size, num_heads=num_heads, dropout=dropout
    )(x, x)
    x = layers.Dropout(dropout)(x)
    res = x + inputs

    # Feed Forward Part
    x = layers.LayerNormalization(epsilon=1e-6)(res)
    x = layers.Conv1D(filters=ff_dim, kernel_size=1, activation="relu")(x)
    x = layers.Dropout(dropout)(x)
    x = layers.Conv1D(filters=inputs.shape[-1], kernel_size=1)(x)
    return x + res

还要确保我们谈论的是相同的包版本

我使用了 numpy (1.21.2) 和 tensorflow (2.6.0) - 试试这些版本，或者让我知道你是否使用了不同的版本。

带有变压器的分类模型的keras模型错误

Error in keras model for classification model with transformers

classification

neural-network

deep-learning

keras

tensorflow