python - TypeError : Dimension value must be integer or None or have an __index__ method, 得到了 TensorShape([None, 1])

Question

我正在尝试将我发现的使用 tflearn 的机器人教程转换为使用 keras。现在输出应该是模型预测的数据。但是，我得到了错误:

TypeError: Dimension value must be integer or None or have an __index__ method, got TensorShape([None, 1])

我的代码:

with open("intents.json") as file:
    data = json.load(file)
try:
    with open("data.pickle", "rb") as f:
        words, lables, training, output = pickle.load(f)

except:
    words = []
    labels = []
    docs_x = []
    docs_y = []

    for intent in data["intents"]:
        for pattern in intent["patterns"]:
            wrds = nltk.word_tokenize(pattern)
            words.extend(wrds)
            docs_x.append(wrds)
            docs_y.append(intent["tag"])

        if intent["tag"] not in labels:
            labels.append(intent["tag"])

    words = [stemmer.stem(w.lower()) for w in words if w != "?"]
    words = sorted(list(set(words)))

    labels = sorted(labels)

    training = []
    output = []

    out_empty = [0 for _ in range(len(labels))]

    for x, doc in enumerate(docs_x):
        bag = []

        wrds = [stemmer.stem(w) for w in doc]

        # marks if a word is present in the input (1=yes, 0=no)
        for w in words:
            if w in wrds:
                bag.append(1)
            else:
                bag.append(0)

        output_row = out_empty[:]
        output_row[labels.index(docs_y[x])] = 1

        training.append(bag)
        output.append(output_row)

    training = numpy.array(training)
    output = numpy.array(output)

    with open("data.pickle", "wb") as f:
        pickle.dump((words, labels, training, output), f)

tf.keras.backend.clear_session()

model = tf.keras.Sequential()

model.add(keras.layers.Dense(len(training[0])))
model.add(keras.layers.Dense(8))
model.add(keras.layers.Dense(8))
model.add(keras.layers.Dense(len(output[0]), activation="softmax"))

try:
    keras.models.load_model("model.tflearn")
except:
    model.compile(optimizer="adam", loss="categorical_crossentropy", metrics="accuracy")
    model.fit(training, output, epochs=1000, batch_size=8)
    model.save("model.tflearn")

def bag_of_words(s, words):
    bag = [0 for _ in range(len(words))]

    s_words = nltk.word_tokenize(s)
    s_words = [stemmer.stem(word.lower()) for word in s_words]

    for se in s_words:
        for i, w in enumerate(words):
            if w == se:
                bag[i] = 1
    return numpy.array(bag)

def chat():
    print("Ready to chat! (type quit to stop)")
    while True:
        inp = input("You: ")
        if inp.lower() == "quit":
            break

        results = model.predict([bag_of_words(inp, words)])
        print(results)

chat()

当使用 Debug模式时，它告诉我错误是行(chat() 内部):

结果 = model.predict([bag_of_words(inp, words)])

Answer 1

好的，所以这并不是真正 100% 回答您的问题，但我在使用 tf.2.2 和 tf.data.Dataset.from_generator 函数搜索相同问题时遇到了它。由于我找到了解决方案，该解决方案未记录在 tf 代码中，因此我想将其发布在这里以供社区将来查看。 output_shapes 只需要与 output_types 相同数量的元素。 IE。说所有 output_types=tf.dtypes.float32 是不够的，而是每个形状元素都需要一个类型元素