Skip to content
TheChatArchiveThe Chat Archive
o1-mini-2024-09-12· OpenAIAi2 WildChat-4.8M (AI2)

from future import printfunction import os os.environ['TFUSELEGACYKERAS'] = '1' from…

  1. User

    from future import print_function import os os.environ['TF_USE_LEGACY_KERAS'] = '1' from tensorflow.python.keras.models import Sequential from tensorflow.python.keras.layers import Dense, Activation import tensorflow as tf from tensorflow.python.keras.regularizers import l2 from tensorflow.python.keras import backend as K, Input from tensorflow.python.keras.optimizer_v2.adam import Adam from sklearn import datasets from sklearn.model_selection import train_test_split from sklearn.preprocessing import OneHotEncoder from sklearn.metrics import roc_curve, auc import numpy as np import matplotlib.pyplot as plt from tensorflow.python.keras.models import Model from importance_sampling.training import ConstantTimeImportanceTraining from example_utils import get_parser

    def plot_history(history): plt.figure(figsize=(12, 5))

    # 绘制训练集和验证集的准确率
    plt.subplot(121)
    plt.plot(history.history['accuracy'])
    plt.plot(history.history['val_accuracy'])
    plt.title('Model accuracy')
    plt.ylabel('Accuracy')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Validation'], loc='upper left')
    
    # 绘制训练集和验证集的损失
    plt.subplot(122)
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('Model loss')
    plt.ylabel('Loss')
    plt.xlabel('Epoch')
    plt.legend(['Train', 'Validation'], loc='upper left')
    
    plt.tight_layout()
    plt.show()
    

    def plot_roc_curve(y_test, y_pred): n_classes = y_test.shape[1] fpr = dict() tpr = dict() roc_auc = dict()

    for i in range(n_classes):
        fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_pred[:, i])
        roc_auc[i] = auc(fpr[i], tpr[i])
    
    # Compute micro-average ROC curve and ROC area
    fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_pred.ravel())
    roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])
    
    plt.figure()
    plt.plot(fpr["micro"], tpr["micro"],
             label='micro-average ROC curve (area = {0:0.2f})'
                   ''.format(roc_auc["micro"]))
    for i in range(n_classes):
        plt.plot(fpr[i], tpr[i],
                 label='ROC curve of class {0} (area = {1:0.2f})'
                       ''.format(i, roc_auc[i]))
    
    plt.plot([0, 1], [0, 1], 'k--')
    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')
    plt.title('Receiver Operating Characteristic (ROC) Curve')
    plt.legend(loc="lower right")
    plt.show()
    

    def calculate_accuracy_fluctuation(history): # 获取每个 epoch 的验证集准确率 val_accuracies = history.history['val_accuracy']

    # 计算平均准确率
    mean_accuracy = np.mean(val_accuracies)
    
    # 计算每个 epoch 的准确率波动(与均值的绝对差值)
    fluctuation = np.sum(np.abs(val_accuracies - mean_accuracy))
    
    return mean_accuracy, fluctuation
    

    if name == "main": parser = get_parser("Train a model on Iris dataset") args = parser.parse_args()

    # 导入数据,分别为输入特征和标签
    iris = datasets.load_iris()
    x_data = iris.data
    y_data = iris.target.reshape(-1, 1)
    
    # 使用OneHotEncoder进行标签的独热编码
    encoder = OneHotEncoder(sparse_output=False)
    y_data = encoder.fit_transform(y_data)
    
    # 分割数据集为训练集和测试集
    x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.3, random_state=116)
    
    # 定义神经网络的超参数
    learning_rate = 0.1
    epochs = 100
    batch_size = 8
    num_classes = 3  # 鸢尾花数据集有3个类别
    
    inputs = Input(shape=(4,))
    x = Dense(10, activation='relu', kernel_regularizer=l2(1e-5))(inputs)
    x = Dense(num_classes, kernel_regularizer=l2(1e-5))(x)
    outputs = Activation('softmax')(x)
    model = Model(inputs=inputs, outputs=outputs)
    
    # 在初始化 ConstantTimeImportanceTraining 之前构建模型
    model.predict(np.zeros((1, 4)))  # 这里用模型的输入形状(1, 4)
    
    # 使用重要性采样训练或常规训练
    if args.importance_training:
        wrapped = ConstantTimeImportanceTraining(model)
    else:
        wrapped = model
    
    history = wrapped.fit(x_train, y_train,
                          batch_size=batch_size,
                          epochs=epochs,
                          verbose=1,
                          validation_data=(x_test, y_test))
    
    score = model.evaluate(x_test, y_test, verbose=0)
    print('Test loss:', score[0])
    print('Test accuracy:', score[1])
    
    # 计算并输出准确率波动
    mean_accuracy, fluctuation = calculate_accuracy_fluctuation(history)
    print('Mean validation accuracy:', mean_accuracy)
    print('Accuracy fluctuation:', fluctuation)
    
    # 绘制训练历史
    plot_history(history)
    
    # 计算预测概率
    y_pred = model.predict(x_test)
    
    # 绘制ROC曲线
    plot_roc_curve(y_test, y_pred)
    

    class _BaseImportanceTraining(object): def init(self, model, score="gnorm", layer=None): """Abstract base class for training a model using importance sampling.

        Arguments
        ---------
            model: The Keras model to train
        """
        # Wrap and transform the model so that it outputs the importance scores
        # and can be used in an importance sampling training scheme
    
        self._check_model(model)
        self.original_model = model
        self.model = OracleWrapper(
            model,
            self.reweighting,
            score=score,
            layer=layer
        )
        self.original_model.optimizer = self.model.optimizer
        signal("is.sample").connect(self._on_sample)
        signal("is.score").connect(self._on_scores)
    
    def _on_sample(self, event):
        self._latest_sample_event = event
    
    def _on_scores(self, scores):
        self._latest_scores = scores
    
    def _check_model(self, model):
        """Check if the model uses Dropout and BatchNorm and warn that it may
        affect the importance calculations."""
        if any(
                isinstance(l, (tf.keras.layers.BatchNormalization, Dropout))
                for l in model.layers
        ):
            sys.stderr.write(("[NOTICE]: You are using BatchNormalization "
                              "and/or Dropout.\nThose layers may affect the "
                              "importance calculations and you are advised "
                              "to exchange them for LayerNormalization or "
                              "BatchNormalization in test mode and L2 "
                              "regularization.\n"))
    
    @property
    def reweighting(self):
        """The reweighting policy that controls the bias of the estimation when
        using importance sampling."""
        raise NotImplementedError()
    
    def sampler(self, dataset, batch_size, steps_per_epoch, epochs):
        """Create a new sampler to sample from the given dataset using
        importance sampling."""
        raise NotImplementedError()
    
    def fit(self, x, y, batch_size=32, epochs=1, verbose=1, callbacks=None,
            validation_split=0.0, validation_data=None, steps_per_epoch=None,
            on_sample=None, on_scores=None):
        """Create an `InMemoryDataset` instance with the given data and train
        the model using importance sampling for a given number of epochs.
    
        Arguments
        ---------
            x: Numpy array of training data or list of numpy arrays
            y: Numpy array of target data
            batch_size: int, number of samples per gradient update
            epochs: int, number of times to iterate over the entire
                    training set
            verbose: {0, >0}, whether to employ the progress bar Keras
                     callback or not
            callbacks: list of Keras callbacks to be called during training
            validation_split: float in [0, 1), percentage of data to use for
                              evaluation
            validation_data: tuple of numpy arrays, Data to evaluate the
                             trained model on without ever training on them
            steps_per_epoch: int or None, number of gradient updates before
                             considering an epoch has passed
            on_sample: callable that accepts the sampler, idxs, w, scores
            on_scores: callable that accepts the sampler and scores
        Returns
        -------
            A Keras `History` object that contains information collected during
            training.
        """
        # Create two data tuples from the given x, y, validation_*
        if validation_data is not None:
            x_train, y_train = x, y
            x_test, y_test = validation_data
    
        elif validation_split > 0:
            assert validation_split < 1, "100% of the data used for testing"
            n = int(round(validation_split * len(x)))
            idxs = np.arange(len(x))
            np.random.shuffle(idxs)
            x_train, y_train = x[idxs[n:]], y[idxs[n:]]
            x_test, y_test = x[idxs[:n]], y[idxs[:n]]
    
        else:
            x_train, y_train = x, y
            x_test, y_test = np.empty(shape=(0, 1)), np.empty(shape=(0, 1))
    
        # Make the dataset to train on
        dataset = InMemoryDataset(
            x_train,
            y_train,
            x_test,
            y_test,
            categorical=False  # this means use the targets as is
        )
    
        return self.fit_dataset(
            dataset=dataset,
            batch_size=batch_size,
            epochs=epochs,
            steps_per_epoch=steps_per_epoch,
            verbose=verbose,
            callbacks=callbacks,
            on_sample=on_sample,
            on_scores=on_scores
        )
    
    def fit_generator(self, train, steps_per_epoch=None, batch_size=32,
                      epochs=1, verbose=1, callbacks=None,
                      validation_data=None, validation_steps=None,
                      on_sample=None, on_scores=None):
        """Create a GeneratorDataset instance and train the model using
        importance sampling for a given number of epochs.
    
        Arguments
        ---------
            train: A generator or iterable that returns tuples (inputs, targets)
            steps_per_epoch: int, number of gradient updates before considering
                             an epoch has passed
            batch_size: int, the number of samples per gradient update
            epochs: int, multiplied by steps_per_epoch denotes the total number
                    of gradient updates
            verbose: {0, >0}, whether to use the progress bar Keras callback
            validation_data: generator, iterable or tuple (inputs, targets)
            validation_steps: None or int, used only if validation_data is a
                              generator
            on_sample: callable that accepts the sampler, idxs, w, scores
            on_scores: callable that accepts the sampler and scores
        """
    
        def infinite_iterator(iterable):
            while True:
                yield from iterable
    
        # 创建验证数据集
        if validation_data is not None:
            if isinstance(validation_data, (tuple, list)):
                test = validation_data
                test_len = None
            elif isinstance(validation_data, Iterable):
                test = infinite_iterator(validation_data)
                try:
                    test_len = len(validation_data) * batch_size
                except TypeError:
                    test_len = validation_steps * batch_size if validation_steps else None
            else:
                test = validation_data
                test_len = validation_steps * batch_size if validation_steps else None
        else:
            test = (np.empty(shape=(0, 1)), np.empty(shape=(0, 1)))
            test_len = None
            logging.info("No validation data provided")
    
        # 设置训练数据和每个 epoch 的步数
        if isinstance(train, Iterable):
            if steps_per_epoch is None:
                try:
                    steps_per_epoch = len(train)
                except TypeError:
                    raise ValueError("steps_per_epoch must be set when using a generator without a __len__ method")
            train = infinite_iterator(train)
        elif steps_per_epoch is None:
            raise ValueError("steps_per_epoch is not set")
    
        dataset = GeneratorDataset(train, test, test_len)
        try:
            print("dataset.train_data=", len(dataset.train_data))
        except Exception as e:
            print(f"Exception occurred: {e}")
    
        return self.fit_dataset(
            dataset=dataset,
            batch_size=batch_size,
            epochs=epochs,
            steps_per_epoch=steps_per_epoch,
            verbose=verbose,
            callbacks=callbacks,
            on_sample=on_sample,
            on_scores=on_scores
        )
    
    def fit_dataset(self, dataset, steps_per_epoch=None, batch_size=32,
                    epochs=1, verbose=1, callbacks=None, on_sample=None,
                    on_scores=None):
        """Train the model on the given dataset for a given number of epochs.
    
        Arguments
        ---------
            dataset: Instance of `BaseDataset` that provides the data
                     to train on.
            steps_per_epoch: int or None, number of gradient updates before
                             considering an epoch has passed. If None it is set
                             to be `len(dataset.train_data) / batch_size`.
            batch_size: int, number of samples per gradient update
            epochs: int, number of times to iterate `steps_per_epoch` times
            verbose: {0, >0}, whether to employ the progress bar Keras
                     callback or not
            callbacks: list of Keras callbacks to be called during training
            on_sample: callable that accepts the sampler, idxs, w, scores
            on_scores: callable that accepts the sampler and scores
        """
        try:
            if len(dataset.train_data) < batch_size:
                raise ValueError(("The model cannot be trained with "
                                  "batch_size > training set"))
        except RuntimeError as e:
            assert "no size" in str(e)
    
        # Set steps_per_epoch properly
        if steps_per_epoch is None:
            steps_per_epoch = len(dataset.train_data) // batch_size
    
        # Create the callbacks list
        # 这段代码的目的是配置和初始化训练过程中将要使用的一组回调函数(callbacks)。
        # 回调函数是在训练的不同阶段被自动调用的函数,用于执行特定的任务,如记录训练指标、
        # 保存模型、早停(early stopping)等
        self.history = History()
        # History是一个回调(Callback),用于在训练过程中记录各种指标(如损失、准确率等)的值
        callbacks = [BaseLogger()] + (callbacks or []) + [self.history]
        if verbose > 0:
            # 添加 ProgbarLogger 回调。ProgbarLogger 用于在终端输出一个进度条,显示训练过程的进度。
            callbacks += [ProgbarLogger(count_mode="steps")]
        callbacks = CallbackList(callbacks)
        callbacks.set_model(self.original_model)
        callbacks.set_params({
            # 设置训练过程的参数
            "epochs": epochs,  # 总共的训练轮数
            "steps": steps_per_epoch,  # 每个 epoch 的步数
            "verbose": verbose,  # 详细程度
            "do_validation": len(dataset.test_data) > 0,  # 是否进行验证
            "metrics": self.metrics_names + [  # 评估指标
                "val_" + n for n in self.metrics_names
            ]
        })
    
        # 创建采样器
        sampler = self.sampler(dataset, batch_size, steps_per_epoch, epochs)
    
        # Start the training loop
        epoch = 0
        self.original_model.stop_training = False
        callbacks.on_train_begin()
        while epoch < epochs:
            # 在每个 epoch 开始时执行一些操作 ,
            # 它会遍历所有在 CallbackList 中注册的回调函数,并调用它们的 on_epoch_begin 方法。
            callbacks.on_epoch_begin(epoch)
    
            for step in range(steps_per_epoch):
                # epoch中的每一step都需要做如下循环
                batch_logs = {"batch": step, "size": batch_size}  # 存储当前批次(batch)训练过程中的相关信息。
                callbacks.on_batch_begin(step, batch_logs)
    
                # Importance sampling is done here
                idxs, (x, y), w = sampler.sample(batch_size)  # 返回被采样的样本
                # Train on the sampled data
                loss, metrics, scores = self.model.train_batch(x, y, w)
                # Update the sampler
                sampler.update(idxs, scores)
    
                values = map(lambda x: x.mean(), [loss] + metrics)
                for l, o in zip(self.metrics_names, values):
                    batch_logs[l] = o
                callbacks.on_batch_end(step, batch_logs)
    
                if on_scores is not None and hasattr(self, "_latest_scores"):
                    on_scores(
                        sampler,
                        self._latest_scores
                    )
    
                if on_sample is not None:
                    on_sample(
                        sampler,
                        self._latest_sample_event["idxs"],
                        self._latest_sample_event["w"],
                        self._latest_sample_event["predicted_scores"]
                    )
    
                if self.original_model.stop_training:
                    break
    
            # Evaluate now that an epoch passed
            epoch_logs = {}
            if len(dataset.test_data) > 0:
                val = self.model.evaluate(
                    *dataset.test_data[:],
                    batch_size=batch_size
                )
                epoch_logs = {
                    "val_" + l: o
                    for l, o in zip(self.metrics_names, val)
                }
            callbacks.on_epoch_end(epoch, epoch_logs)
            if self.original_model.stop_training:
                break
            epoch += 1
        callbacks.on_train_end()
    
        return self.history
    
    @property
    def metrics_names(self):
        def name(x):
            if isinstance(x, str):
                return x
            if hasattr(x, "name"):
                return x.name
            if hasattr(x, "__name__"):
                return x.__name__
            return str(x)
    
        metrics = self.original_model.metrics or []
        return (
                ["loss"] +
                [name(m) for m in metrics] +
                ["score"]
        )
    

    class _UnbiasedImportanceTraining(_BaseImportanceTraining): def init(self, model, score="gnorm", layer=None): self._reweighting = BiasedReweightingPolicy(1.0) # no bias

        super(_UnbiasedImportanceTraining, self).__init__(model, score, layer)
    
    @property
    def reweighting(self):
        return self._reweighting
    

    class ConstantTimeImportanceTraining(_UnbiasedImportanceTraining): """主要目的是通过保持每次迭代的时间常量的同时,提高梯度的质量来加速模型训练。

    Arguments
    ---------
        model: The Keras model to train
        score: {"gnorm", "loss", "full_gnorm"}, the importance metric to use
               for importance sampling
        layer: None or int or Layer, the layer to compute the gnorm with
    """
    
    def __init__(self, model, backward_time=2.0, score="gnorm", layer=None):
        self._backward_time = backward_time
    
        super(ConstantTimeImportanceTraining, self).__init__(
            model,
            score,
            layer
        )
    
    def sampler(self, dataset, batch_size, steps_per_epoch, epochs):
        return ConstantTimeSampler(
            dataset,
            self.reweighting,
            self.model,
            backward_time=self._backward_time
        )
    

    上述代码报错Traceback (most recent call last): File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\examples\yuanweihua.py", line 260, in wrapped = ConstantTimeImportanceTraining(model) File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\importance_sampling\training.py", line 466, in init super(ConstantTimeImportanceTraining, self).init( File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\importance_sampling\training.py", line 363, in init super(_UnbiasedImportanceTraining, self).init(model, score, layer) File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\importance_sampling\training.py", line 40, in init self.model = OracleWrapper( File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\importance_sampling\model_wrappers.py", line 172, in init self._augment_model(model, score, reweighting) File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\importance_sampling\model_wrappers.py", line 206, in _augment_model loss = model.loss AttributeError: 'Functional' object has no attribute 'loss'

    Process finished with exit code 1 怎么解决

  2. Assistant

    The error you're encountering:

    AttributeError: 'Functional' object has no attribute 'loss'
    

    indicates that the Keras Model object (Functional API) you're working with does not have a loss attribute set. In Keras, the loss attribute is assigned when you compile the model using the model.compile() method. Without compiling, certain attributes and configurations required for training are missing, which leads to the error you're seeing.

    Solution: Compile the Model Before Wrapping

    To resolve this issue, you need to compile your model before passing it to the ConstantTimeImportanceTraining wrapper. Here's how you can modify your code:

    1. Add the model.compile() Call:

      After defining your model architecture and before calling model.predict, add the model.compile() method. This method configures the model for training by specifying the optimizer, loss function, and any metrics you want to track.

    2. Specify Appropriate Parameters:

      For the Iris dataset, which is a multi-class classification problem, you typically use categorical_crossentropy as the loss function and an optimizer like Adam. Additionally, tracking the accuracy metric is standard.

    Updated Code Snippet

    Here's how you can incorporate these changes into your existing script:

    # ... [previous code remains unchanged] ...
    
    # Define the model architecture
    inputs = Input(shape=(4,))
    x = Dense(10, activation='relu', kernel_regularizer=l2(1e-5))(inputs)
    x = Dense(num_classes, kernel_regularizer=l2(1e-5))(x)
    outputs = Activation('softmax')(x)
    model = Model(inputs=inputs, outputs=outputs)
    
    # **Compile the model before wrapping**
    model.compile(
        optimizer=Adam(learning_rate=learning_rate),
        loss='categorical_crossentropy',
        metrics=['accuracy']
    )
    
    # Initialize the model (ensure input shape matches)
    model.predict(np.zeros((1, 4)))
    
    # Use importance sampling training or conventional training
    if args.importance_training:
        wrapped = ConstantTimeImportanceTraining(model)
    else:
        wrapped = model
    
    # ... [rest of your training and evaluation code] ...
    

    Additional Recommendations

    1. Ensure All Dependencies Are Correct:

      • Verify that the importance_sampling package is compatible with your TensorFlow and Keras versions. Sometimes, outdated or incompatible packages can cause unexpected errors.
      • Make sure that all necessary classes and functions (like OracleWrapper, BiasedReweightingPolicy, History, etc.) are correctly imported and implemented.
    2. Check for Other Missing Configurations:

      • Ensure that any other required configurations for the importance_sampling wrapper are correctly set. For instance, if the wrapper expects certain metrics or specific model properties, make sure they're provided.
    3. Debugging Tips:

      • If you continue to encounter issues, consider adding print statements or using a debugger to inspect the state of the model object before and after wrapping.
      • Ensure that the model.loss is correctly set after compiling by printing model.loss:
        print("Model loss:", model.loss)
        

    Conclusion

    By compiling the model before wrapping it with the ConstantTimeImportanceTraining, you establish the necessary configurations for training, thereby resolving the AttributeError. This step ensures that all attributes, including loss, are properly set, allowing the training process to proceed without interruptions.

    If you follow these steps and ensure that your model is correctly compiled, the error should be resolved, and you should be able to proceed with training your model using importance sampling.


    References:

    Add a call to model.compile(...) with appropriate loss and optimizer before wrapping the model. For example, insert model.compile(optimizer=Adam(learning_rate), loss='categorical_crossentropy', metrics=['accuracy']) after defining the model and before initializing ConstantTimeImportanceTraining.