这是一个创建于 1979 天前的主题，其中的信息可能已经有所发展或是发生改变。
MBP16 i9-9880h 5500M 8G
#!/usr/bin/env python # coding: utf-8 import tensorflow.compat.v2 as tf import tensorflow_datasets as tfds tf.enable_v2_behavior() from tensorflow.python.framework.ops import disable_eager_execution disable_eager_execution() from tensorflow.python.compiler.mlcompute import mlcompute mlcompute.set_mlc_device(device_name='cpu') (ds_train, ds_test), ds_info = tfds.load( 'mnist', split=['train', 'test'], shuffle_files=True, as_supervised=True, with_info=True, ) def normalize_img(image, label): """Normalizes images: `uint8` -> `float32`.""" return tf.cast(image, tf.float32) / 255., label ds_train = ds_train.map( normalize_img, num_parallel_calls=tf.data.experimental.AUTOTUNE) ds_train = ds_train.cache() ds_train = ds_train.shuffle(ds_info.splits['train'].num_examples) ds_train = ds_train.batch(128) ds_train = ds_train.prefetch(tf.data.experimental.AUTOTUNE) ds_test = ds_test.map( normalize_img, num_parallel_calls=tf.data.experimental.AUTOTUNE) ds_test = ds_test.batch(128) ds_test = ds_test.cache() ds_test = ds_test.prefetch(tf.data.experimental.AUTOTUNE) model = tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape=(28, 28, 1)), tf.keras.layers.Dense(128, activation='relu'), tf.keras.layers.Dense(10, activation='softmax') ]) model.compile( loss='sparse_categorical_crossentropy', optimizer=tf.keras.optimizers.Adam(0.001), metrics=['accuracy'], ) model.fit( ds_train, epochs=10, ) GPU 速度
Epoch 1/10 469/469 [==============================] - 10s 14ms/step - batch: 234.0000 - size: 1.0000 - loss: 0.3598 - accuracy: 0.9028
Epoch 2/10 469/469 [==============================] - 9s 14ms/step - batch: 234.0000 - size: 1.0000 - loss: 0.1623 - accuracy: 0.9535
Epoch 3/10 469/469 [==============================] - 9s 14ms/step - batch: 234.0000 - size: 1.0000 - loss: 0.1182 - accuracy: 0.9664
Epoch 4/10 469/469 [==============================] - 9s 14ms/step - batch: 234.0000 - size: 1.0000 - loss: 0.0911 - accuracy: 0.9735
Epoch 5/10 469/469 [==============================] - 9s 14ms/step - batch: 234.0000 - size: 1.0000 - loss: 0.0732 - accuracy: 0.9786
CPU 速度
Epoch 1/10 469/469 [==============================] - 3s 1ms/step - batch: 234.0000 - size: 1.0000 - loss: nan - accuracy: 0.0987
Epoch 2/10 469/469 [==============================] - 3s 1ms/step - batch: 234.0000 - size: 1.0000 - loss: nan - accuracy: 0.0987
Epoch 3/10 469/469 [==============================] - 3s 1ms/step - batch: 234.0000 - size: 1.0000 - loss: nan - accuracy: 0.0987
Epoch 4/10 469/469 [==============================] - 3s 1ms/step - batch: 234.0000 - size: 1.0000 - loss: nan - accuracy: 0.0987
Epoch 5/10 469/469 [==============================] - 3s 1ms/step - batch: 234.0000 - size: 1.0000 - loss: nan - accuracy: 0.0987
 | 1 tzm41 2020 年 11 月 22 日 via iPhone 浅窄的 dense net，GPU 没啥加速效果吧… |
 | 2 RichardSun 2020 年 11 月 22 日 via iPhone 想起之前我试过一个好像叫 plaidML 的 backend，随便跑了下试试 GPU 模式比普通 backend 的 CPU 都慢♂ |
 | 3 ZRS 2020 年 11 月 22 日 via iPhone 试试 resnet50 |
 | 4 shiltian 2020 年 11 月 22 日 via iPhone 我一直想写一个 Metal 的 OpenMP offloading plugin，但是 Metal compiler 没开源，我搞不定 CodeGen… |
 | 5 sharpy OP @tianshilei1992 #4 你可以看看 https://github.com/a2flo/floor.git 这个项目，也许有点儿启发，这个项目修改了 clang 的源码，使之能生成各个后端代码，看说明是“compiles compute/graphics C++ code to CUDA/PTX, Metal/AIR, OpenCL/SPIR/SPIR-V, Vulkan/SPIR-V code/binaries ” |
Select Language