前言

因为众所周知的原因，TensorFlow 和 PyTorch 等深度学习架构，只能在NVIDIA 的 GPU 下运行，对于 Mac 上的 AMD 的 GPU 并不支持。本来不关心这个问题，但是在机缘巧合执行问了下chatGPT，手上正好有个过时的MacBook Pro，就此尝试。

以下是chatGPT原文：
在深度学习过程中，显卡的性能对模型的训练速度和效果有重大影响。由于您用的是AMD显卡的Mac电脑，因此与NVIDIA显卡相比，您可能需要额外安装AMD显卡适配的深度学习库来支持GPU加速训练。

具体来说，您可以使用Keras或PyTorch这样的深度学习库，并选择适合您的显卡类型的版本。例如，Keras有支持AMD显卡的版本，您可以安装AMD版本的Keras，以充分利用您的Mac电脑上AMD显卡的计算性能。在使用GPU进行深度学习训练时，使用较新的AMD显卡会比老旧的显卡更快、更稳定。

此外，您可能还需要了解一些基本的GPU加速训练的技巧，例如，将数据靠近计算设备，减少数据读取时间、缓存数据、使用更高效的算法等等，可以进一步提高深度学习训练的效率和效果。

安装

pip install plaidml-keras

完成安装后，还需要让代码适配本机的 GPU 。

plaidml-setup

上代码

import plaidml.keras

plaidml.keras.install_backend()
import os

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

os.environ["KERAS_BACKEND"] = "plaidml.keras.backend"


def test_speed_of_device(use_tensorflow=False):
    '''Trains a simple convnet on the MNIST dataset.
    Gets to 99.25% test accuracy after 12 epochs
    (there is still a lot of margin for parameter tuning).
    16 seconds per epoch on a GRID K520 GPU.
    '''
    batch_size = 128
    num_classes = 10
    epochs = 12

    # input image dimensions
    img_rows, img_cols = 28, 28

    # the data, split between train and test sets
    (x_train, y_train), (x_test, y_test) = mnist.load_data()

    if K.image_data_format() == 'channels_first':
        x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
        x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
        input_shape = (1, img_rows, img_cols)
    else:
        x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
        x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
        input_shape = (img_rows, img_cols, 1)

    x_train = x_train.astype('float32')
    x_test = x_test.astype('float32')
    x_train /= 255
    x_test /= 255
    print('x_train shape:', x_train.shape)
    print(x_train.shape[0], 'train samples')
    print(x_test.shape[0], 'test samples')

    # convert class vectors to binary class matrices
    y_train = keras.utils.to_categorical(y_train, num_classes)
    y_test = keras.utils.to_categorical(y_test, num_classes)

    model = Sequential()
    model.add(Conv2D(32, kernel_size=(3, 3),
                     activation='relu',
                     input_shape=input_shape))
    model.add(Conv2D(64, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(num_classes, activation='softmax'))

    model.compile(loss=keras.losses.categorical_crossentropy,
                  optimizer=keras.optimizers.Adadelta(),
                  metrics=['accuracy'])

    model.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])


if __name__ == '__main__':
    os.environ["PLAIDML_DEVICE_IDS"] = "metal_amd_radeon_pro_5600m.0"
    test_speed_of_device()