# googleColaboratory2-UKujX90xLHo. using keras in colaboratory
<![CDATA[
# @
# You can use gpu in colaboratory for keras
# ref: https://keras.io/utils/#multi_gpu_model
# @
# Memory infomation
!cat /proc/meminfo
# MemTotal: 13341960 kB
# MemFree: 8533256 kB
# MemAvailable: 12413480 kB
# Buffers: 592664 kB
# Cached: 3106704 kB
# SwapCached: 0 kB
# Active: 2154112 kB
# Inactive: 1833004 kB
# Active(anon): 457024 kB
# Inactive(anon): 114432 kB
# Active(file): 1697088 kB
# Inactive(file): 1718572 kB
# Unevictable: 0 kB
# Mlocked: 0 kB
# SwapTotal: 0 kB
# SwapFree: 0 kB
# Dirty: 380 kB
# Writeback: 0 kB
# AnonPages: 287764 kB
# Mapped: 164784 kB
# Shmem: 283716 kB
# Slab: 746368 kB
# SReclaimable: 717980 kB
# SUnreclaim: 28388 kB
# KernelStack: 3184 kB
# PageTables: 4448 kB
# NFS_Unstable: 0 kB
# Bounce: 0 kB
# WritebackTmp: 0 kB
# CommitLimit: 6670980 kB
# Committed_AS: 1548724 kB
# VmallocTotal: 34359738367 kB
# VmallocUsed: 0 kB
# VmallocChunk: 0 kB
# AnonHugePages: 0 kB
# HugePages_Total: 0
# HugePages_Free: 0
# HugePages_Rsvd: 0
# HugePages_Surp: 0
# Hugepagesize: 2048 kB
# DirectMap4k: 384972 kB
# DirectMap2M: 10100736 kB
# DirectMap1G: 5242880 kB
!cat /proc/cpuinfo
# processor : 0
# vendor_id : GenuineIntel
# cpu family : 6
# model : 63
# model name : Intel(R) Xeon(R) CPU @ 2.30GHz
# stepping : 0
# microcode : 0x1
# cpu MHz : 2300.000
# cache size : 46080 KB
# physical id : 0
# siblings : 2
# core id : 0
# cpu cores : 1
# apicid : 0
# initial apicid : 0
# fpu : yes
# fpu_exception : yes
# cpuid level : 13
# wp : yes
# flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc eagerfpu pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms xsaveopt
# bugs :
# bogomips : 4600.00
# clflush size : 64
# cache_alignment : 64
# address sizes : 46 bits physical, 48 bits virtual
# power management:
# processor : 1
# vendor_id : GenuineIntel
# cpu family : 6
# model : 63
# model name : Intel(R) Xeon(R) CPU @ 2.30GHz
# stepping : 0
# microcode : 0x1
# cpu MHz : 2300.000
# cache size : 46080 KB
# physical id : 0
# siblings : 2
# core id : 0
# cpu cores : 1
# apicid : 1
# initial apicid : 1
# fpu : yes
# fpu_exception : yes
# cpuid level : 13
# wp : yes
# flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc eagerfpu pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms xsaveopt
# bugs :
# bogomips : 4600.00
# clflush size : 64
# cache_alignment : 64
# address sizes : 46 bits physical, 48 bits virtual
# power management:
# https://keras.io/
# install and import keras
!pip install -q keras
import keras
# Using TensorFlow as keras' backend.
import tensorflow as tf
from keras.applications import Xception
from keras.utils import multi_gpu_model
import numpy as np
num_samples = 100
height = 71
width = 71
num_classes = 100
# I first run model by cpu
with tf.device('/cpu:0'):
model = Xception(weights=None,
input_shape=(height, width, 3),
classes=num_classes)
# We can't use 8 gpu in colaboratory
# But if we use 1 gpu, it also triggers error with saying use over 2 gpu
# In conclusion, we can't use multi_gpu_model of keras
# We will replace this code with following code
parallel_model = multi_gpu_model(model, gpus=1)
parallel_model.compile(loss='categorical_crossentropy',
optimizer='rmsprop')
# Generate dummy data.
x = np.random.random((num_samples, height, width, 3))
y = np.random.random((num_samples, num_classes))
# This `fit` call will be distributed on 8 GPUs.
# Since the batch size is 256, each GPU will process 32 samples.
parallel_model.fit(x, y, epochs=20, batch_size=256)
# Save model via the template model (which shares the same weights):
model.save('my_model.h5')
# ---------------------------------------------------------------------------
# ValueError Traceback (most recent call last)
# <ipython-input-6-4353c6d558e3> in <module>()
# 6 # Replicates the model on 8 GPUs.
# 7 # This assumes that your machine has 8 available GPUs.
# ----> 8 parallel_model = multi_gpu_model(model, gpus=1)
# 9 parallel_model.compile(loss='categorical_crossentropy',
# 10 optimizer='rmsprop')
# /usr/local/lib/python3.6/dist-packages/keras/utils/training_utils.py in multi_gpu_model(model, gpus)
# 121 raise ValueError('For multi-gpu usage to be effective, '
# 122 'call `multi_gpu_model` with `gpus >= 2`. '
# --> 123 'Received: `gpus=%d`' % gpus)
# 124 num_gpus = gpus
# 125 target_gpu_ids = range(num_gpus)
# ValueError: For multi-gpu usage to be effective, call `multi_gpu_model` with `gpus >= 2`. Received: `gpus=1`
from tensorflow.python.client import device_lib
print(device_lib.list_local_devices())
# < [name: "/device:CPU:0"
# < device_type: "CPU"
# < memory_limit: 268435456
# < locality {
# < }
# < incarnation: 4221312434634366830
# < , name: "/device:GPU:0"
# < device_type: "GPU"
# < memory_limit: 356515840
# < locality {
# < bus_id: 1
# < }
# < incarnation: 11454811533186484289
# < physical_device_desc: "device: 0, name: Tesla K80, pci bus id: 0000:00:04.0, compute capability: 3.7"
# < ]
import datetime
# We will process same task with gpu
start = datetime.datetime.now()
with tf.device('/gpu:0'):
model = Xception(weights=None,
input_shape=(height, width, 3),
classes=num_classes)
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop')
# Generate dummy data.
x = np.random.random((num_samples, height, width, 3))
y = np.random.random((num_samples, num_classes))
model.fit(x, y, epochs=3, batch_size=16)
model.save('my_model.h5')
# < end = datetime.datetime.now()
# < time_delta = end - start
# < Epoch 1/3
# < 100/100 [==============================] - 7s 66ms/step - loss: 235.2676
# < Epoch 2/3
# < 100/100 [==============================] - 1s 11ms/step - loss: 231.3431
# < Epoch 3/3
# < 100/100 [==============================] - 1s 11ms/step - loss: 228.3584
# < print('Taking time: {} seconds'.format(time_delta.seconds))
# < Taking time: 29 seconds
# We will process same task with cpu
start = datetime.datetime.now()
with tf.device('/cpu:0'):
model = Xception(weights=None,
input_shape=(height, width, 3),
classes=num_classes)
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop')
# Generate dummy data.
x = np.random.random((num_samples, height, width, 3))
y = np.random.random((num_samples, num_classes))
model.fit(x, y, epochs=3, batch_size=16)
model.save('my_model.h5')
# < end = datetime.datetime.now()
# < time_delta = end - start
# < Epoch 1/3
# < 100/100 [==============================] - 25s 248ms/step - loss: 271.1356
# < Epoch 2/3
# < 100/100 [==============================] - 19s 187ms/step - loss: 258.8897
# < Epoch 3/3
# < 100/100 [==============================] - 19s 186ms/step - loss: 247.9633
# < print('Taking time: {} seconds'.format(time_delta.seconds))
# < Taking time: 88 seconds
]]>