from future import printfunction import os os.environ['TFUSELEGACYKERAS'] = '1' from…
- 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, fluctuationif 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 model = Sequential() model.add(Dense(10, activation='relu', input_shape=(4,), kernel_regularizer=l2(1e-5))) model.add(Dense(num_classes, kernel_regularizer=l2(1e-5))) model.add(Activation('softmax')) # **在包装之前编译模型** model.compile( optimizer=Adam(learning_rate=learning_rate), loss='categorical_crossentropy', metrics=['accuracy'] ) # 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 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 )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._reweightingdef _tolist(x, acceptable_iterables=(list, tuple)): if not isinstance(x, acceptable_iterables): x = [x] return x
def _get_scoring_layer(score, y_true, y_pred, loss="categorical_crossentropy", layer=None, model=None): """Get a scoring layer that computes the score for each pair of y_true, y_pred""" assert score in ["loss", "gnorm", "full_gnorm", "acc"]
if score == "loss": return LossLayer(loss)([ y_true, y_pred ]) elif score == "gnorm": return GradientNormLayer( layer.output, loss, fast=True )([ y_true, y_pred ]) elif score == "full_gnorm": return GradientNormLayer( model.trainable_weights, loss, fast=False )([ y_true, y_pred ]) elif score == "acc": return LossLayer(categorical_accuracy)([ y_true, y_pred ])class ModelWrapper(object): """The goal of the ModelWrapper is to take a NN and add some extra layers that produce a score, a loss and the sample weights to perform importance sampling.""" def _iterate_batches(self, x, y, batch_size): bs = batch_size for s in range(0, len(y), bs): yield [xi[s:s+bs] for xi in _tolist(x)], y[s:s+bs]
def evaluate(self, x, y, batch_size=128): result = np.mean( np.vstack([ self.evaluate_batch(xi, yi) for xi, yi in self._iterate_batches(x, y, batch_size) ]), axis=0 ) signal("is.evaluation").send(result) return result def score(self, x, y, batch_size=128): bs = batch_size result = np.hstack([ self.score_batch(xi, yi).T for xi, yi in self._iterate_batches(x, y, batch_size) ]).T signal("is.score").send(result) return result def set_lr(self, lr): """Set the learning rate of the wrapped models. We try to set the learning rate on a member variable model and a member variable small. If we do not find a member variable model we raise a NotImplementedError """ try: K.set_value( self.optimizer.lr, lr ) except AttributeError: try: K.set_value( self.model.optimizer.lr, lr ) except AttributeError: raise NotImplementedError() try: K.set_value( self.small.optimizer.lr, lr ) except AttributeError: pass def evaluate_batch(self, x, y): raise NotImplementedError() def score_batch(self, x, y): raise NotImplementedError() def train_batch(self, x, y, w): raise NotImplementedError()class GradientNormLayer(Layer): """GradientNormLayer aims to output the gradient norm given a list of parameters (whose gradient to compute) and a loss function to combine the two inputs.
# Arguments parameter_list: A list of Keras variables to compute the gradient norm for loss: The loss function to use to combine the model output and the target into a scalar and then compute the gradient norm fast: If set to True it means we know that the gradient with respect to each sample only affects one part of the parameter list so we can use the batch mode to compute the gradient """ def __init__(self, parameter_list, loss, fast=False, **kwargs): self.supports_masking = True self.parameter_list = parameter_list self.loss = losses.get(loss) self.fast = fast super(GradientNormLayer, self).__init__(**kwargs) def compute_mask(self, inputs, input_mask): return None def build(self, input_shape): pass # Nothing to do super(GradientNormLayer, self).build(input_shape) def compute_output_shape(self, input_shape): # We get two inputs assert len(input_shape) == 2 return (input_shape[0][0], 1) def call(self, x, mask=None): # x should be an output and a target assert len(x) == 2 losses = _per_sample_loss(self.loss, mask, x) if self.fast: grads = K.sqrt(K.sum([ self._sum_per_sample(K.square(g)) for g in K.gradients(losses, self.parameter_list) ])) else: nb_samples = K.shape(losses)[0] grads = K.map_fn( lambda i: self._grad_norm(losses[i]), K.arange(0, nb_samples), dtype=K.floatx() ) return K.reshape(grads, (-1, 1)) def _sum_per_sample(self, x): """Sum across all the dimensions except the batch dim""" # Instead we might be able to use x.ndims but there have been problems # with ndims and Keras so I think len(int_shape()) is more reliable dims = len(K.int_shape(x)) return K.sum(x, axis=list(range(1, dims))) def _grad_norm(self, loss): grads = K.gradients(loss, self.parameter_list) return K.sqrt( sum([ K.sum(K.square(g)) for g in grads ]) )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 132, 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 226, in augment_model score_tensor = get_scoring_layer( File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\importance_sampling\model_wrappers.py", line 41, in get_scoring_layer return GradientNormLayer( File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 983, in call return self.functional_construction_call(inputs, args, kwargs, File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1121, in functional_construction_call outputs = self.keras_tensor_symbolic_call( File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 854, in keras_tensor_symbolic_call return self.infer_output_signature(inputs, args, kwargs, input_masks) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 894, in infer_output_signature outputs = call_fn(inputs, *args, **kwargs) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\autograph\impl\api.py", line 692, in wrapper raise e.ag_error_metadata.to_exception(e) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\autograph\impl\api.py", line 689, in wrapper return converted_call(f, args, kwargs, options=options) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\autograph\impl\api.py", line 439, in converted_call result = converted_f(*effective_args, **kwargs) File "C:\Users\LIUWEN~1\AppData\Local\Temp_autograph_generated_filek3u6uuvd.py", line 30, in tf__call ag.if_stmt(ag.ld(self).fast, if_body, else_body, get_state, set_state, ('grads',), 1) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\autograph\operators\control_flow.py", line 1363, in if_stmt py_if_stmt(cond, body, orelse) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\autograph\operators\control_flow.py", line 1416, in py_if_stmt return body() if cond else orelse() File "C:\Users\LIUWEN~1\AppData\Local\Temp_autograph_generated_filek3u6uuvd.py", line 22, in if_body grads = ag.converted_call(ag.ld(K).sqrt, (ag.converted_call(ag.ld(K).sum, ([ag.converted_call(ag_.ld(self).sum_per_sample, (ag_.converted_call(ag__.ld(K).square, (ag__.ld(g),), None, fscope),), None, fscope) for g in ag__.converted_call(ag__.ld(K).gradients, (ag__.ld(losses), ag__.ld(self).parameter_list), None, fscope)],), None, fscope),), None, fscope) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\autograph\impl\api.py", line 377, in converted_call return _call_unconverted(f, args, kwargs, options) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\autograph\impl\api.py", line 459, in _call_unconverted return f(*args) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\keras\backend.py", line 4143, in gradients return gradients_module.gradients( File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\ops\gradients_impl.py", line 165, in gradients return gradients_util._GradientsHelper( File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\ops\gradients_util.py", line 536, in _GradientsHelper xs = ops.internal_convert_n_to_tensor_or_indexed_slices( File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\framework\indexed_slices.py", line 366, in internal_convert_n_to_tensor_or_indexed_slices internal_convert_to_tensor_or_indexed_slices( File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\framework\indexed_slices.py", line 327, in internal_convert_to_tensor_or_indexed_slices return ops.convert_to_tensor(value, dtype=dtype, name=name, as_ref=as_ref) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\profiler\trace.py", line 183, in wrapped return func(*args, **kwargs) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\framework\ops.py", line 1638, in convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\framework\constant_op.py", line 343, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\framework\constant_op.py", line 267, in constant return _constant_impl(value, dtype, shape, name, verify_shape=False, File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\framework\constant_op.py", line 284, in _constant_impl tensor_util.make_tensor_proto( File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 432, in make_tensor_proto values = np.asarray(values) File "C:\Users\liuwenjing.conda\envs\pennylane_qiskit\lib\site-packages\tensorflow\python\keras\engine\keras_tensor.py", line 254, in array raise TypeError( TypeError: in user code:
File "C:\代码备份库\importance-sampling-master-yuanweihua-QNN-pennylane\importance_sampling\layers\scores.py", line 119, in call * grads = K.sqrt(K.sum([ TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.Process finished with exit code 1 如何进行修改,用中文进行表述
- Assistant
您的代码在运行时出现了如下错误:
TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.这个错误提示说,您正在尝试将一个符号化的 Keras 输入/输出传递给一个 NumPy 调用,这在 TensorFlow 2.x 中不被支持。这通常是由于在计算图模式下执行需要立即执行的操作导致的。
问题分析:
具体到您的代码,错误发生在
GradientNormLayer类的call方法中,当fast=True时,会出现上述错误:class GradientNormLayer(Layer): def call(self, x, mask=None): ... if self.fast: grads = K.sqrt(K.sum([ self._sum_per_sample(K.square(g)) for g in K.gradients(losses, self.parameter_list) ])) else: ...在
fast=True的情况下,K.gradients函数尝试对losses张量计算梯度。但是在 TensorFlow 2.x 中,K.gradients无法对一个非标量(如按样本计算的损失)计算梯度。解决方法:
要解决这个问题,您需要将
GradientNormLayer的fast参数设置为False,这样它会使用逐样本计算的方式,避免了对非标量计算梯度的问题。具体修改步骤如下:
-
定位到
_get_scoring_layer函数找到您的代码中的
_get_scoring_layer函数,该函数用于根据不同的评分标准返回相应的评分层。 -
修改
GradientNormLayer的fast参数在该函数中,找到针对
score == "gnorm"的分支,将fast参数从True改为False。具体代码修改如下:修改前:
elif score == "gnorm": return GradientNormLayer( layer.output, loss, fast=True )([ y_true, y_pred ])修改后:
elif score == "gnorm": return GradientNormLayer( layer.output, loss, fast=False )([ y_true, y_pred ]) -
保存并重新运行代码
修改完成后,保存您的代码文件,然后重新运行脚本,看看是否解决了问题。
注意事项:
-
将
fast参数设置为False,可能会使得梯度计算变得稍微慢一些,因为它需要对每个样本逐一计算梯度。但是,这可以确保代码在 TensorFlow 2.x 中正常运行。 -
如果您需要优化性能,可以考虑进一步修改
GradientNormLayer,使其兼容 TensorFlow 2.x 的计算方式,例如使用tf.GradientTape或其他矢量化操作。 -
确保您的 TensorFlow 和 Keras 版本匹配,并且代码中没有其他使用过时 API 的地方。
总结:
通过将
GradientNormLayer的fast参数设置为False,您可以避免在计算梯度时出现对非标量求导的错误,从而解决当前的问题。希望以上回答能够帮助您顺利解决问题。
-