https://keras.io/keras_3/
Keras 3.0 升级是对 Keras 的全面重写,引入了一系列令人振奋的新特性,为深度学习领域带来了全新的可能性。
Keras 3.0 的最大亮点之一是支持多框架。Keras 3 实现了完整的 Keras API,并使其可用于 TensorFlow、JAX 和 PyTorch —— 包括一百多个层、数十种度量标准、损失函数、优化器和回调函数,以及 Keras 的训练和评估循环,以及 Keras 的保存和序列化基础设施。所有您熟悉和喜爱的 API 都在这里。
新版本的 Keras 为大规模模型训练和部署提供了全新的能力。借助优化的算法和性能改进,现在您可以处理更大规模、更复杂的深度学习模型,而无需担心性能问题。
Keras 3 的 fit()
/evaluate()
/predict()
例程兼容 tf.data.Dataset
对象、PyTorch 的 DataLoader
对象、NumPy 数组和 Pandas 数据框,无论您使用的是哪个后端。您可以在 PyTorch 的 DataLoader
上训练 Keras 3 + TensorFlow 模型,或者在 tf.data.Dataset
上训练 Keras 3 + PyTorch 模型。
https://keras.io/guides/custom_train_step_in_torch/
导入环境
- import os
-
- # This guide can only be run with the torch backend.
- os.environ["KERAS_BACKEND"] = "torch"
-
- import torch
- import keras
- from keras import layers
- import numpy as np
定义模型
在 train_step()
方法的主体中,实现了一个常规的训练更新,类似于您已经熟悉的内容。重要的是,我们通过 self.compute_loss()
计算损失,它包装了传递给 compile()
的损失函数。
- class CustomModel(keras.Model):
- def train_step(self, data):
- # Unpack the data. Its structure depends on your model and
- # on what you pass to `fit()`.
- x, y = data
-
- # Call torch.nn.Module.zero_grad() to clear the leftover gradients
- # for the weights from the previous train step.
- self.zero_grad()
-
- # Compute loss
- y_pred = self(x, training=True) # Forward pass
- loss = self.compute_loss(y=y, y_pred=y_pred)
-
- # Call torch.Tensor.backward() on the loss to compute gradients
- # for the weights.
- loss.backward()
-
- trainable_weights = [v for v in self.trainable_weights]
- gradients = [v.value.grad for v in trainable_weights]
-
- # Update weights
- with torch.no_grad():
- self.optimizer.apply(gradients, trainable_weights)
-
- # Update metrics (includes the metric that tracks the loss)
- for metric in self.metrics:
- if metric.name == "loss":
- metric.update_state(loss)
- else:
- metric.update_state(y, y_pred)
-
- # Return a dict mapping metric names to current value
- # Note that it will include the loss (tracked in self.metrics).
- return {m.name: m.result() for m in self.metrics}
训练模型
- # Construct and compile an instance of CustomModel
- inputs = keras.Input(shape=(32,))
- outputs = keras.layers.Dense(1)(inputs)
- model = CustomModel(inputs, outputs)
- model.compile(optimizer="adam", loss="mse", metrics=["mae"])
-
- # Just use `fit` as usual
- x = np.random.random((1000, 32))
- y = np.random.random((1000, 1))
- model.fit(x, y, epochs=3)
https://keras.io/guides/writing_a_custom_training_loop_in_torch/
导入环境
- import os
-
- # This guide can only be run with the torch backend.
- os.environ["KERAS_BACKEND"] = "torch"
-
- import torch
- import keras
- from keras import layers
- import numpy as np
定义模型、加载数据集
- # Let's consider a simple MNIST model
- def get_model():
- inputs = keras.Input(shape=(784,), name="digits")
- x1 = keras.layers.Dense(64, activation="relu")(inputs)
- x2 = keras.layers.Dense(64, activation="relu")(x1)
- outputs = keras.layers.Dense(10, name="predictions")(x2)
- model = keras.Model(inputs=inputs, outputs=outputs)
- return model
-
-
- # Create load up the MNIST dataset and put it in a torch DataLoader
- # Prepare the training dataset.
- batch_size = 32
- (x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
- x_train = np.reshape(x_train, (-1, 784)).astype("float32")
- x_test = np.reshape(x_test, (-1, 784)).astype("float32")
- y_train = keras.utils.to_categorical(y_train)
- y_test = keras.utils.to_categorical(y_test)
-
- # Reserve 10,000 samples for validation.
- x_val = x_train[-10000:]
- y_val = y_train[-10000:]
- x_train = x_train[:-10000]
- y_train = y_train[:-10000]
-
- # Create torch Datasets
- train_dataset = torch.utils.data.TensorDataset(
- torch.from_numpy(x_train), torch.from_numpy(y_train)
- )
- val_dataset = torch.utils.data.TensorDataset(
- torch.from_numpy(x_val), torch.from_numpy(y_val)
- )
-
- # Create DataLoaders for the Datasets
- train_dataloader = torch.utils.data.DataLoader(
- train_dataset, batch_size=batch_size, shuffle=True
- )
- val_dataloader = torch.utils.data.DataLoader(
- val_dataset, batch_size=batch_size, shuffle=False
- )
定义优化器
- # Instantiate a torch optimizer
- model = get_model()
- optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
-
- # Instantiate a torch loss function
- loss_fn = torch.nn.CrossEntropyLoss()
训练模型
- epochs = 3
- for epoch in range(epochs):
- for step, (inputs, targets) in enumerate(train_dataloader):
- # Forward pass
- logits = model(inputs)
- loss = loss_fn(logits, targets)
-
- # Backward pass
- model.zero_grad()
- loss.backward()
-
- # Optimizer variable updates
- optimizer.step()
-
- # Log every 100 batches.
- if step % 100 == 0:
- print(
- f"Training loss (for 1 batch) at step {step}: {loss.detach().numpy():.4f}"
- )
- print(f"Seen so far: {(step + 1) * batch_size} samples")