[深度应用]·主流深度学习硬件速度对比（CPU，GPU，TPU）

from tensorflow import keras

from keras.datasets import cifar10

import numpy as np

batch_size = 100
num_classes = 10
epochs = 10

# 数据载入
(x_train, train_labels), (x_test, test_labels) = cifar10.load_data()

print(x_train.shape)

train_images = x_train.reshape([-1,32,32,3]) / 255.0
test_images = x_test.reshape([-1,32,32,3]) / 255.0


model = keras.Sequential([
    #(-1,32,32,3)->(-1,32,32,16)
    keras.layers.Conv2D(input_shape=(32, 32, 3),filters=32,kernel_size=3,strides=1,padding='same'),     # Padding method),
    #(-1,32,32,32)->(-1,32,32,32)
    keras.layers.Conv2D(filters=32,kernel_size=3,strides=1,padding='same'),     # Padding method),
    #(-1,32,32,32)->(-1,16,16,32)
    keras.layers.MaxPool2D(pool_size=2,strides=2,padding='same'),
    #(-1,16,16,32)->(-1,16,16,64)
    keras.layers.Conv2D(filters=64,kernel_size=3,strides=1,padding='same'),     # Padding method),
    #(-1,16,16,64)->(-1,16,16,64)
    keras.layers.Conv2D(filters=64,kernel_size=3,strides=1,padding='same'),     # Padding method),
    #(-1,16,16,64)->(-1,8,8,64)
    keras.layers.MaxPool2D(pool_size=2,strides=2,padding='same'),
    #(-1,8,8,64)->(-1,8*8*128)
    keras.layers.Conv2D(filters=128,kernel_size=3,strides=1,padding='same'),     # Padding method),
    #(-1,8,8,128)->(-1,8*8*128)
    keras.layers.Conv2D(filters=128,kernel_size=3,strides=1,padding='same'),     # Padding method),
    #(-1,8,8,128)->(-1,8*8*128)
    keras.layers.Flatten(),
    #(-1,8*8*128)->(-1,256)
    keras.layers.Dropout(0.3),
    keras.layers.Dense(128, activation="relu"),
    #(-1,256)->(-1,10)
    keras.layers.Dense(10, activation="softmax")
])

print(model.summary())

model.compile(optimizer="adam",
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(train_images, train_labels, batch_size = batch_size, epochs=epochs,validation_data=[test_images[:1000],test_labels[:1000]])

test_loss, test_acc = model.evaluate(test_images, test_labels)

print(np.argmax(model.predict(test_images[:20]),1),test_labels[:20])

python demo.py
Using TensorFlow backend.
(50000, 32, 32, 3)
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
conv2d (Conv2D)              (None, 32, 32, 32)        896
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 32, 32, 32)        9248
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 16, 16, 32)        0
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 16, 16, 64)        18496
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 16, 16, 64)        36928
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 8, 8, 64)          0
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 8, 8, 128)         73856
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 8, 8, 128)         147584
_________________________________________________________________
flatten (Flatten)            (None, 8192)              0
_________________________________________________________________
dropout (Dropout)            (None, 8192)              0
_________________________________________________________________
dense (Dense)                (None, 128)               1048704
_________________________________________________________________
dense_1 (Dense)              (None, 10)                1290
=================================================================
Total params: 1,337,002
Trainable params: 1,337,002
Non-trainable params: 0
_________________________________________________________________
None
Train on 50000 samples, validate on 1000 samples
Epoch 1/10
2019-03-15 17:07:34.477745: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-03-15 17:07:34.552699: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:964] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-03-15 17:07:34.553036: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.6325
pciBusID: 0000:01:00.0
totalMemory: 10.92GiB freeMemory: 10.68GiB
2019-03-15 17:07:34.553049: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0
2019-03-15 17:07:34.737306: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-03-15 17:07:34.737335: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988]      0
2019-03-15 17:07:34.737340: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0:   N
2019-03-15 17:07:34.737468: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10327 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)
50000/50000 [==============================] - 5s 103us/step - loss: 1.3343 - acc: 0.5256 - val_loss: 1.0300 - val_acc: 0.6450
Epoch 2/10
50000/50000 [==============================] - 4s 76us/step - loss: 0.9668 - acc: 0.6660 - val_loss: 0.8930 - val_acc: 0.6820
Epoch 3/10
50000/50000 [==============================] - 4s 76us/step - loss: 0.8349 - acc: 0.7097 - val_loss: 0.8486 - val_acc: 0.7130
Epoch 4/10
50000/50000 [==============================] - 4s 76us/step - loss: 0.7496 - acc: 0.7412 - val_loss: 0.8823 - val_acc: 0.7040
Epoch 5/10
50000/50000 [==============================] - 4s 76us/step - loss: 0.6805 - acc: 0.7643 - val_loss: 0.8710 - val_acc: 0.7060
Epoch 6/10
50000/50000 [==============================] - 4s 76us/step - loss: 0.6256 - acc: 0.7833 - val_loss: 0.9150 - val_acc: 0.7020
Epoch 7/10
50000/50000 [==============================] - 4s 77us/step - loss: 0.5715 - acc: 0.8000 - val_loss: 0.8586 - val_acc: 0.7140
Epoch 8/10
50000/50000 [==============================] - 4s 76us/step - loss: 0.5312 - acc: 0.8143 - val_loss: 0.9455 - val_acc: 0.7030
Epoch 9/10
50000/50000 [==============================] - 4s 77us/step - loss: 0.4878 - acc: 0.8287 - val_loss: 1.0063 - val_acc: 0.7360
Epoch 10/10
50000/50000 [==============================] - 4s 76us/step - loss: 0.4474 - acc: 0.8438 - val_loss: 1.0609 - val_acc: 0.7030
10000/10000 [==============================] - 1s 54us/step
[3 8 8 0 6 6 1 6 3 1 4 9 4 7 9 8 5 5 8 6] 
[[3]
 [8]
 [8]
 [0]
 [6]
 [6]
 [1]
 [6]
 [3]
 [1]
 [0]
 [9]
 [5]
 [7]
 [9]
 [8]
 [5]
 [7]
 [8]
 [6]]