SunGaofeng
6 years ago
commit
c1fa2ec360
File diff suppressed because it is too large
Load Diff
@ -1,42 +0,0 @@
|
||||
FROM ubuntu:16.04
|
||||
MAINTAINER PaddlePaddle Authors <paddle-dev@baidu.com>
|
||||
|
||||
ARG UBUNTU_MIRROR
|
||||
RUN /bin/bash -c 'if [[ -n ${UBUNTU_MIRROR} ]]; then sed -i 's#http://archive.ubuntu.com/ubuntu#${UBUNTU_MIRROR}#g' /etc/apt/sources.list; fi'
|
||||
|
||||
# ENV variables
|
||||
ARG ANDROID_ABI
|
||||
ARG ANDROID_API
|
||||
|
||||
ENV ANDROID_ABI=${ANDROID_ABI:-"armeabi-v7a"}
|
||||
ENV ANDROID_API=${ANDROID_API:-21}
|
||||
|
||||
ENV HOME=/root \
|
||||
ANDROID_NDK_HOME=/opt/android-ndk-linux \
|
||||
ANDROID_TOOLCHAINS_DIR=/opt/toolchains
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y \
|
||||
git python-dev python-pip python-numpy \
|
||||
wget curl tar unzip gcc g++ locales clang-format-3.8 swig cmake && \
|
||||
apt-get clean -y
|
||||
|
||||
# git credential to skip password typing
|
||||
RUN git config --global credential.helper store
|
||||
|
||||
# Fix locales to en_US.UTF-8
|
||||
RUN localedef -i en_US -f UTF-8 en_US.UTF-8
|
||||
|
||||
RUN pip install --upgrade pip==9.0.3 && \
|
||||
pip install -U 'protobuf==3.1.0' && \
|
||||
pip install -U wheel sphinx && \
|
||||
pip install pre-commit
|
||||
|
||||
# Android NDK
|
||||
RUN mkdir -p ${ANDROID_TOOLCHAINS_DIR} && \
|
||||
mkdir -p /opt/android-ndk-tmp && \
|
||||
cd /opt/android-ndk-tmp && \
|
||||
wget -q https://dl.google.com/android/repository/android-ndk-r14b-linux-x86_64.zip && \
|
||||
unzip -q android-ndk-r14b-linux-x86_64.zip && \
|
||||
mv android-ndk-r14b ${ANDROID_NDK_HOME} && \
|
||||
rm -rf /opt/android-ndk-tmp
|
||||
@ -1,168 +0,0 @@
|
||||
# Benchmark
|
||||
|
||||
Machine:
|
||||
|
||||
- CPU: 12-core Intel(R) Xeon(R) CPU E5-2620 v2 @2.10GHz
|
||||
- GPU: Tesla K40m
|
||||
- cuDNN: v5.1
|
||||
- system: Docker 1.12.1, all platforms are tested in docker environment.
|
||||
|
||||
Platforms:
|
||||
|
||||
- PaddlePaddle: paddledev/paddle:gpu-devel-v0.9.0a0
|
||||
- Tensorflow: gcr.io/tensorflow/tensorflow:0.11.0rc0-gpu
|
||||
- Caffe: kaixhin/cuda-caffe
|
||||
|
||||
Several convolutional neural networks and recurrent neural networks are used to test.
|
||||
|
||||
## Image
|
||||
|
||||
### Benchmark Model
|
||||
|
||||
AlexNet, GoogleNet and a small network used in Caffe.
|
||||
|
||||
- [AlexNet](https://github.com/BVLC/caffe/tree/master/models/bvlc_alexnet): but the group size is one.
|
||||
|
||||
- [GoogleNet](https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet): but remove loss1 and loss2 when testing benchmark.
|
||||
|
||||
- [SmallNet](https://github.com/BVLC/caffe/blob/master/examples/cifar10/cifar10\_quick\_train\_test.prototxt)
|
||||
|
||||
|
||||
### Single-GPU
|
||||
|
||||
- AlexNet: input - 3 * 227 * 227, Time: ms/batch
|
||||
|
||||
| BatchSize | 64 | 128 | 256 | 512 |
|
||||
|--------------|-----| -----| ------| -----|
|
||||
| PaddlePaddle | 195 | 334 | 602 | 1629 |
|
||||
| TensorFlow | 223 | 364 | 645 | 1235 |
|
||||
| Caffe | 324 | 627 | 1232 | 2513 |
|
||||
|
||||
**Notation**
|
||||
|
||||
All platforms use cuDNN-v5.1. We see that caffe is slower in this experiment, because its workspace limit size of cuDNN-conv interface is 8 * 1024 * 1024, which is smaller in PaddlePaddle and TensorFlow. Note that Caffe will be faster if increasing the workspace limit size.
|
||||
|
||||
- GoogletNet: input - 3 * 224 * 224, Time: ms/batch
|
||||
|
||||
|
||||
| BatchSize | 64 | 128 | 256 |
|
||||
|--------------|-------| -------| --------|
|
||||
| PaddlePaddle | 613 | 1149 | 2348 |
|
||||
| TensorFlow | 644 | 1176 | 2219 |
|
||||
| Caffe | 694 | 1364 | out of memory |
|
||||
|
||||
- SmallNet: input - 3 * 32 * 32, Time ms/batch
|
||||
|
||||
| BatchSize | 64 | 128 | 256 | 512 |
|
||||
|--------------|--------| -------- | --------|---------|
|
||||
| PaddlePaddle | 10.463 | 18.184 | 33.113 | 63.039 |
|
||||
| TensorFlow | 9 | 15 | 28 | 59 |
|
||||
| Caffe | 9.373 | 16.6606 | 31.4797 | 59.719 |
|
||||
|
||||
**Notation**
|
||||
|
||||
All the single-GPU experiments in caffe use `caffe time` to calculate elapsed time, which does not include parameter updating time. However, both PaddlePaddle and TensorFlow experiments contain the parameter updating time. As compared with the total time, this part is relatively little on single machine, we can ignore it.
|
||||
|
||||
In Tensorflow, they implement algorithm searching method instead of using the algorithm searching interface in cuDNN.
|
||||
|
||||
### Multi-GPU: 4 GPUs
|
||||
|
||||
- AlexNet, ms / batch
|
||||
|
||||
| total-BatchSize | 128 * 4 | 256 * 4 |
|
||||
|------------------|----------| -----------|
|
||||
| PaddlePaddle | 347 | 622 |
|
||||
| TensorFlow | 377 | 675 |
|
||||
| Caffe | 1229 | 2435 |
|
||||
|
||||
For example, if `total-BatchSize = 128 * 4`, the speedup ratio is calculated by
|
||||
|
||||
```
|
||||
time_at_1gpu_batch_128 * 4 / time_at_4gpu_total_batch_512
|
||||
= (334 * 4)/347
|
||||
= 3.85
|
||||
```
|
||||
|
||||
<img src="figs/alexnet-4gpu.png" width="420">
|
||||
|
||||
|
||||
- GoogleNet, ms / batch
|
||||
|
||||
| total-BatchSize | 128 * 4 | 256 * 4 |
|
||||
|-------------------|--------------| ----------- |
|
||||
| PaddlePaddle | 1178 | 2367 |
|
||||
| TensorFlow | 1210 | 2292 |
|
||||
| Caffe | 2007 | out of memory |
|
||||
|
||||
<img src="figs/googlenet-4gpu.png" width="420">
|
||||
|
||||
|
||||
## RNN
|
||||
We use lstm network for text classfication to test benchmark.
|
||||
|
||||
### Dataset
|
||||
- [IMDB](http://www.iro.umontreal.ca/~lisa/deep/data/imdb.pkl)
|
||||
- Sequence length is 100. In fact, PaddlePaddle supports training with variable-length sequence, but TensorFlow needs to pad. Thus, we also pad sequence length to 100 in PaddlePaddle in order to compare.
|
||||
- Dictionary size=30000
|
||||
- Peephole connection is used in `lstmemory` by default in PaddlePaddle. It is also configured in TensorFlow.
|
||||
|
||||
### Single-GPU
|
||||
|
||||
#### LSTM in Text Classification
|
||||
|
||||
Testing `2 lstm layer + fc` network with different hidden size and batch size.
|
||||
|
||||
- Batch size = 64, ms / batch
|
||||
|
||||
| hidden_size | 256 | 512 | 1280 |
|
||||
|--------------|-------| -------| --------|
|
||||
| PaddlePaddle | 83 | 184 | 641 |
|
||||
| TensorFlow | 175 | 280 | 818 |
|
||||
|
||||
- Batch size = 128, ms / batch
|
||||
|
||||
| hidden_size | 256 | 512 | 1280 |
|
||||
|--------------|------- | -------| --------|
|
||||
| PaddlePaddle | 110 | 261 | 1007 |
|
||||
| TensorFlow | 181 | 361 | 1237 |
|
||||
|
||||
|
||||
- Batch size = 256, ms / batch
|
||||
|
||||
| hidden_size | 256 | 512 | 1280 |
|
||||
|--------------|-------| -------| --------|
|
||||
| PaddlePaddle | 170 | 414 | 1655 |
|
||||
| TensorFlow | 238 | 536 | 1905 |
|
||||
|
||||
<img src="figs/rnn_lstm_cls.png" width="600">
|
||||
|
||||
#### Seq2Seq
|
||||
|
||||
The benchmark of sequence-to-sequence network will be added later.
|
||||
|
||||
|
||||
### Multi GPU: 4 GPUs
|
||||
|
||||
#### LSTM in Text Classification
|
||||
|
||||
- hidden_size = 256, ms / batch
|
||||
|
||||
| batch_size | 256 | 512 |
|
||||
|--------------| -------| --------|
|
||||
| PaddlePaddle | 90 | 118 |
|
||||
| TensorFlow | 226 | 118 |
|
||||
|
||||
|
||||
- hidden_size = 512, ms / batch
|
||||
|
||||
| batch_size | 256 | 512 |
|
||||
|--------------| -------| --------|
|
||||
| PaddlePaddle | 189 | 268 |
|
||||
| TensorFlow | 297 | 383 |
|
||||
|
||||
|
||||
<img src="figs/rnn_lstm_4gpus.png" width="420">
|
||||
|
||||
#### Seq2Seq
|
||||
|
||||
The benchmark of sequence-to-sequence network will be added later.
|
||||
@ -1,93 +0,0 @@
|
||||
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
from paddle.trainer_config_helpers import *
|
||||
|
||||
height = 227
|
||||
width = 227
|
||||
num_class = 1000
|
||||
batch_size = get_config_arg('batch_size', int, 128)
|
||||
gp = get_config_arg('layer_num', int, 1)
|
||||
is_infer = get_config_arg("is_infer", bool, False)
|
||||
num_samples = get_config_arg('num_samples', int, 2560)
|
||||
|
||||
args = {
|
||||
'height': height,
|
||||
'width': width,
|
||||
'color': True,
|
||||
'num_class': num_class,
|
||||
'is_infer': is_infer,
|
||||
'num_samples': num_samples
|
||||
}
|
||||
define_py_data_sources2(
|
||||
"train.list" if not is_infer else None,
|
||||
"test.list" if is_infer else None,
|
||||
module="provider",
|
||||
obj="process",
|
||||
args=args)
|
||||
|
||||
settings(
|
||||
batch_size=batch_size,
|
||||
learning_rate=0.01 / batch_size,
|
||||
learning_method=MomentumOptimizer(0.9),
|
||||
regularization=L2Regularization(0.0005 * batch_size))
|
||||
|
||||
# conv1
|
||||
net = data_layer('data', size=height * width * 3)
|
||||
net = img_conv_layer(
|
||||
input=net,
|
||||
filter_size=11,
|
||||
num_channels=3,
|
||||
num_filters=96,
|
||||
stride=4,
|
||||
padding=1)
|
||||
net = img_cmrnorm_layer(input=net, size=5, scale=0.0001, power=0.75)
|
||||
net = img_pool_layer(input=net, pool_size=3, stride=2)
|
||||
|
||||
# conv2
|
||||
net = img_conv_layer(
|
||||
input=net, filter_size=5, num_filters=256, stride=1, padding=2, groups=gp)
|
||||
net = img_cmrnorm_layer(input=net, size=5, scale=0.0001, power=0.75)
|
||||
net = img_pool_layer(input=net, pool_size=3, stride=2)
|
||||
|
||||
# conv3
|
||||
net = img_conv_layer(
|
||||
input=net, filter_size=3, num_filters=384, stride=1, padding=1)
|
||||
# conv4
|
||||
net = img_conv_layer(
|
||||
input=net, filter_size=3, num_filters=384, stride=1, padding=1, groups=gp)
|
||||
|
||||
# conv5
|
||||
net = img_conv_layer(
|
||||
input=net, filter_size=3, num_filters=256, stride=1, padding=1, groups=gp)
|
||||
net = img_pool_layer(input=net, pool_size=3, stride=2)
|
||||
|
||||
net = fc_layer(
|
||||
input=net,
|
||||
size=4096,
|
||||
act=ReluActivation(),
|
||||
layer_attr=ExtraAttr(drop_rate=0.5))
|
||||
net = fc_layer(
|
||||
input=net,
|
||||
size=4096,
|
||||
act=ReluActivation(),
|
||||
layer_attr=ExtraAttr(drop_rate=0.5))
|
||||
net = fc_layer(input=net, size=1000, act=SoftmaxActivation())
|
||||
|
||||
if is_infer:
|
||||
outputs(net)
|
||||
else:
|
||||
lab = data_layer('label', num_class)
|
||||
loss = cross_entropy(input=net, label=lab)
|
||||
outputs(loss)
|
||||
@ -1,245 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
from paddle.trainer_config_helpers import *
|
||||
|
||||
height = 224
|
||||
width = 224
|
||||
num_class = 1000
|
||||
batch_size = get_config_arg('batch_size', int, 128)
|
||||
use_gpu = get_config_arg('use_gpu', bool, True)
|
||||
is_infer = get_config_arg("is_infer", bool, False)
|
||||
num_samples = get_config_arg('num_samples', int, 2560)
|
||||
|
||||
args = {
|
||||
'height': height,
|
||||
'width': width,
|
||||
'color': True,
|
||||
'num_class': num_class,
|
||||
'is_infer': is_infer,
|
||||
'num_samples': num_samples
|
||||
}
|
||||
define_py_data_sources2(
|
||||
"train.list" if not is_infer else None,
|
||||
"test.list" if is_infer else None,
|
||||
module="provider",
|
||||
obj="process",
|
||||
args=args)
|
||||
|
||||
settings(
|
||||
batch_size=batch_size,
|
||||
learning_rate=0.01 / batch_size,
|
||||
learning_method=MomentumOptimizer(0.9),
|
||||
regularization=L2Regularization(0.0005 * batch_size))
|
||||
|
||||
conv_projection = conv_projection if use_gpu else img_conv_layer
|
||||
|
||||
def inception2(name, input, channels, \
|
||||
filter1,
|
||||
filter3R, filter3,
|
||||
filter5R, filter5,
|
||||
proj):
|
||||
|
||||
conv1 = name + '_1'
|
||||
conv3r = name + '_3r'
|
||||
conv3 = name + '_3'
|
||||
conv5r = name + '_5r'
|
||||
conv5 = name + '_5'
|
||||
maxpool = name + '_max'
|
||||
convproj = name + '_proj'
|
||||
|
||||
cov1 = img_conv_layer(
|
||||
name=conv1,
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_channels=channels,
|
||||
num_filters=filter1,
|
||||
stride=1,
|
||||
padding=0)
|
||||
|
||||
cov3r = img_conv_layer(
|
||||
name=conv3r,
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_channels=channels,
|
||||
num_filters=filter3R,
|
||||
stride=1,
|
||||
padding=0)
|
||||
cov3 = img_conv_layer(
|
||||
name=conv3,
|
||||
input=cov3r,
|
||||
filter_size=3,
|
||||
num_filters=filter3,
|
||||
stride=1,
|
||||
padding=1)
|
||||
|
||||
cov5r = img_conv_layer(
|
||||
name=conv5r,
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_channels=channels,
|
||||
num_filters=filter5R,
|
||||
stride=1,
|
||||
padding=0)
|
||||
cov5 = img_conv_layer(
|
||||
name=conv5,
|
||||
input=cov5r,
|
||||
filter_size=5,
|
||||
num_filters=filter5,
|
||||
stride=1,
|
||||
padding=2)
|
||||
|
||||
pool1 = img_pool_layer(
|
||||
name=maxpool,
|
||||
input=input,
|
||||
pool_size=3,
|
||||
num_channels=channels,
|
||||
stride=1,
|
||||
padding=1)
|
||||
covprj = img_conv_layer(
|
||||
name=convproj,
|
||||
input=pool1,
|
||||
filter_size=1,
|
||||
num_filters=proj,
|
||||
stride=1,
|
||||
padding=0)
|
||||
|
||||
cat = concat_layer(name=name, input=[cov1, cov3, cov5, covprj])
|
||||
return cat
|
||||
|
||||
def inception(name, input, channels, \
|
||||
filter1,
|
||||
filter3R, filter3,
|
||||
filter5R, filter5,
|
||||
proj):
|
||||
|
||||
cov1 = conv_projection(
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_channels=channels,
|
||||
num_filters=filter1,
|
||||
stride=1,
|
||||
padding=0)
|
||||
|
||||
cov3r = img_conv_layer(
|
||||
name=name + '_3r',
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_channels=channels,
|
||||
num_filters=filter3R,
|
||||
stride=1,
|
||||
padding=0)
|
||||
cov3 = conv_projection(
|
||||
input=cov3r, filter_size=3, num_filters=filter3, stride=1, padding=1)
|
||||
|
||||
cov5r = img_conv_layer(
|
||||
name=name + '_5r',
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_channels=channels,
|
||||
num_filters=filter5R,
|
||||
stride=1,
|
||||
padding=0)
|
||||
cov5 = conv_projection(
|
||||
input=cov5r, filter_size=5, num_filters=filter5, stride=1, padding=2)
|
||||
|
||||
pool1 = img_pool_layer(
|
||||
name=name + '_max',
|
||||
input=input,
|
||||
pool_size=3,
|
||||
num_channels=channels,
|
||||
stride=1,
|
||||
padding=1)
|
||||
covprj = conv_projection(
|
||||
input=pool1, filter_size=1, num_filters=proj, stride=1, padding=0)
|
||||
|
||||
cat = concat_layer(
|
||||
name=name,
|
||||
input=[cov1, cov3, cov5, covprj],
|
||||
bias_attr=True if use_gpu else False,
|
||||
act=ReluActivation())
|
||||
return cat
|
||||
|
||||
|
||||
data = data_layer(name="input", size=3 * height * width)
|
||||
|
||||
# stage 1
|
||||
conv1 = img_conv_layer(
|
||||
name="conv1",
|
||||
input=data,
|
||||
filter_size=7,
|
||||
num_channels=3,
|
||||
num_filters=64,
|
||||
stride=2,
|
||||
padding=3)
|
||||
pool1 = img_pool_layer(
|
||||
name="pool1", input=conv1, pool_size=3, num_channels=64, stride=2)
|
||||
|
||||
# stage 2
|
||||
conv2_1 = img_conv_layer(
|
||||
name="conv2_1",
|
||||
input=pool1,
|
||||
filter_size=1,
|
||||
num_filters=64,
|
||||
stride=1,
|
||||
padding=0)
|
||||
conv2_2 = img_conv_layer(
|
||||
name="conv2_2",
|
||||
input=conv2_1,
|
||||
filter_size=3,
|
||||
num_filters=192,
|
||||
stride=1,
|
||||
padding=1)
|
||||
pool2 = img_pool_layer(
|
||||
name="pool2", input=conv2_2, pool_size=3, num_channels=192, stride=2)
|
||||
|
||||
# stage 3
|
||||
ince3a = inception("ince3a", pool2, 192, 64, 96, 128, 16, 32, 32)
|
||||
ince3b = inception("ince3b", ince3a, 256, 128, 128, 192, 32, 96, 64)
|
||||
pool3 = img_pool_layer(
|
||||
name="pool3", input=ince3b, num_channels=480, pool_size=3, stride=2)
|
||||
|
||||
# stage 4
|
||||
ince4a = inception("ince4a", pool3, 480, 192, 96, 208, 16, 48, 64)
|
||||
ince4b = inception("ince4b", ince4a, 512, 160, 112, 224, 24, 64, 64)
|
||||
ince4c = inception("ince4c", ince4b, 512, 128, 128, 256, 24, 64, 64)
|
||||
ince4d = inception("ince4d", ince4c, 512, 112, 144, 288, 32, 64, 64)
|
||||
ince4e = inception("ince4e", ince4d, 528, 256, 160, 320, 32, 128, 128)
|
||||
pool4 = img_pool_layer(
|
||||
name="pool4", input=ince4e, num_channels=832, pool_size=3, stride=2)
|
||||
|
||||
# stage 5
|
||||
ince5a = inception("ince5a", pool4, 832, 256, 160, 320, 32, 128, 128)
|
||||
ince5b = inception("ince5b", ince5a, 832, 384, 192, 384, 48, 128, 128)
|
||||
pool5 = img_pool_layer(
|
||||
name="pool5",
|
||||
input=ince5b,
|
||||
num_channels=1024,
|
||||
pool_size=7,
|
||||
stride=7,
|
||||
pool_type=AvgPooling())
|
||||
|
||||
# We remove loss1 and loss2 for all system when testing benchmark
|
||||
# output 1
|
||||
# pool_o1 = img_pool_layer(name="pool_o1", input=ince4a, num_channels=512, pool_size=5, stride=3, pool_type=AvgPooling())
|
||||
# conv_o1 = img_conv_layer(name="conv_o1", input=pool_o1, filter_size=1, num_filters=128, stride=1, padding=0)
|
||||
# fc_o1 = fc_layer(name="fc_o1", input=conv_o1, size=1024, layer_attr=ExtraAttr(drop_rate=0.7), act=ReluActivation())
|
||||
# out1 = fc_layer(name="output1", input=fc_o1, size=1000, act=SoftmaxActivation())
|
||||
# loss1 = cross_entropy(name='loss1', input=out1, label=lab, coeff=0.3)
|
||||
|
||||
# output 2
|
||||
#pool_o2 = img_pool_layer(name="pool_o2", input=ince4d, num_channels=528, pool_size=5, stride=3, pool_type=AvgPooling())
|
||||
#conv_o2 = img_conv_layer(name="conv_o2", input=pool_o2, filter_size=1, num_filters=128, stride=1, padding=0)
|
||||
#fc_o2 = fc_layer(name="fc_o2", input=conv_o2, size=1024, layer_attr=ExtraAttr(drop_rate=0.7), act=ReluActivation())
|
||||
#out2 = fc_layer(name="output2", input=fc_o2, size=1000, act=SoftmaxActivation())
|
||||
#loss2 = cross_entropy(name='loss2', input=out2, label=lab, coeff=0.3)
|
||||
|
||||
# output 3
|
||||
dropout = dropout_layer(name="dropout", input=pool5, dropout_rate=0.4)
|
||||
out3 = fc_layer(
|
||||
name="output3", input=dropout, size=1000, act=SoftmaxActivation())
|
||||
|
||||
if is_infer:
|
||||
outputs(out3)
|
||||
else:
|
||||
lab = data_layer(name="label", size=num_class)
|
||||
loss3 = cross_entropy(name='loss3', input=out3, label=lab)
|
||||
outputs(loss3)
|
||||
@ -1,114 +0,0 @@
|
||||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import sys
|
||||
import argparse
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser('Parse Log')
|
||||
parser.add_argument(
|
||||
'--file_path', '-f', type=str, help='the path of the log file')
|
||||
parser.add_argument(
|
||||
'--sample_rate',
|
||||
'-s',
|
||||
type=float,
|
||||
default=1.0,
|
||||
help='the rate to take samples from log')
|
||||
parser.add_argument(
|
||||
'--log_period', '-p', type=int, default=1, help='the period of log')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def parse_file(file_name):
|
||||
loss = []
|
||||
error = []
|
||||
with open(file_name) as f:
|
||||
for i, line in enumerate(f):
|
||||
line = line.strip()
|
||||
if not line.startswith('pass'):
|
||||
continue
|
||||
line_split = line.split(' ')
|
||||
if len(line_split) != 5:
|
||||
continue
|
||||
|
||||
loss_str = line_split[2][:-1]
|
||||
cur_loss = float(loss_str.split('=')[-1])
|
||||
loss.append(cur_loss)
|
||||
|
||||
err_str = line_split[3][:-1]
|
||||
cur_err = float(err_str.split('=')[-1])
|
||||
error.append(cur_err)
|
||||
|
||||
accuracy = [1.0 - err for err in error]
|
||||
|
||||
return loss, accuracy
|
||||
|
||||
|
||||
def sample(metric, sample_rate):
|
||||
interval = int(1.0 / sample_rate)
|
||||
if interval > len(metric):
|
||||
return metric[:1]
|
||||
|
||||
num = len(metric) / interval
|
||||
idx = [interval * i for i in range(num)]
|
||||
metric_sample = [metric[id] for id in idx]
|
||||
return metric_sample
|
||||
|
||||
|
||||
def plot_metric(metric,
|
||||
batch_id,
|
||||
graph_title,
|
||||
line_style='b-',
|
||||
line_label='y',
|
||||
line_num=1):
|
||||
plt.figure()
|
||||
plt.title(graph_title)
|
||||
if line_num == 1:
|
||||
plt.plot(batch_id, metric, line_style, label=line_label)
|
||||
else:
|
||||
for i in range(line_num):
|
||||
plt.plot(batch_id, metric[i], line_style[i], label=line_label[i])
|
||||
plt.xlabel('batch')
|
||||
plt.ylabel(graph_title)
|
||||
plt.legend()
|
||||
plt.savefig(graph_title + '.jpg')
|
||||
plt.close()
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
assert args.sample_rate > 0. and args.sample_rate <= 1.0, "The sample rate should in the range (0, 1]."
|
||||
|
||||
loss, accuracy = parse_file(args.file_path)
|
||||
batch = [args.log_period * i for i in range(len(loss))]
|
||||
|
||||
batch_sample = sample(batch, args.sample_rate)
|
||||
loss_sample = sample(loss, args.sample_rate)
|
||||
accuracy_sample = sample(accuracy, args.sample_rate)
|
||||
|
||||
plot_metric(loss_sample, batch_sample, 'loss', line_label='loss')
|
||||
plot_metric(
|
||||
accuracy_sample,
|
||||
batch_sample,
|
||||
'accuracy',
|
||||
line_style='g-',
|
||||
line_label='accuracy')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@ -1,47 +0,0 @@
|
||||
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
import io, os
|
||||
import random
|
||||
import numpy as np
|
||||
from paddle.trainer.PyDataProvider2 import *
|
||||
|
||||
|
||||
def initHook(settings, height, width, color, num_class, **kwargs):
|
||||
settings.height = height
|
||||
settings.width = width
|
||||
settings.color = color
|
||||
settings.num_class = num_class
|
||||
if settings.color:
|
||||
settings.data_size = settings.height * settings.width * 3
|
||||
else:
|
||||
settings.data_size = settings.height * settings.width
|
||||
settings.is_infer = kwargs.get('is_infer', False)
|
||||
settings.num_samples = kwargs.get('num_samples', 2560)
|
||||
if settings.is_infer:
|
||||
settings.slots = [dense_vector(settings.data_size)]
|
||||
else:
|
||||
settings.slots = [dense_vector(settings.data_size), integer_value(1)]
|
||||
|
||||
|
||||
@provider(
|
||||
init_hook=initHook, min_pool_size=-1, cache=CacheType.CACHE_PASS_IN_MEM)
|
||||
def process(settings, file_list):
|
||||
for i in xrange(settings.num_samples):
|
||||
img = np.random.rand(1, settings.data_size).reshape(-1, 1).flatten()
|
||||
if settings.is_infer:
|
||||
yield img.astype('float32')
|
||||
else:
|
||||
lab = random.randint(0, settings.num_class - 1)
|
||||
yield img.astype('float32'), int(lab)
|
||||
@ -1,230 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
from paddle.trainer_config_helpers import *
|
||||
|
||||
height = 224
|
||||
width = 224
|
||||
num_class = 1000
|
||||
batch_size = get_config_arg('batch_size', int, 64)
|
||||
layer_num = get_config_arg("layer_num", int, 50)
|
||||
is_infer = get_config_arg("is_infer", bool, False)
|
||||
num_samples = get_config_arg('num_samples', int, 2560)
|
||||
|
||||
args = {
|
||||
'height': height,
|
||||
'width': width,
|
||||
'color': True,
|
||||
'num_class': num_class,
|
||||
'is_infer': is_infer,
|
||||
'num_samples': num_samples
|
||||
}
|
||||
define_py_data_sources2(
|
||||
"train.list" if not is_infer else None,
|
||||
"test.list" if is_infer else None,
|
||||
module="provider",
|
||||
obj="process",
|
||||
args=args)
|
||||
|
||||
settings(
|
||||
batch_size=batch_size,
|
||||
learning_rate=0.01 / batch_size,
|
||||
learning_method=MomentumOptimizer(0.9),
|
||||
regularization=L2Regularization(0.0005 * batch_size))
|
||||
|
||||
|
||||
#######################Network Configuration #############
|
||||
def conv_bn_layer(name,
|
||||
input,
|
||||
filter_size,
|
||||
num_filters,
|
||||
stride,
|
||||
padding,
|
||||
channels=None,
|
||||
active_type=ReluActivation()):
|
||||
"""
|
||||
A wrapper for conv layer with batch normalization layers.
|
||||
Note:
|
||||
conv layer has no activation.
|
||||
"""
|
||||
|
||||
tmp = img_conv_layer(
|
||||
name=name + "_conv",
|
||||
input=input,
|
||||
filter_size=filter_size,
|
||||
num_channels=channels,
|
||||
num_filters=num_filters,
|
||||
stride=stride,
|
||||
padding=padding,
|
||||
act=LinearActivation(),
|
||||
bias_attr=False)
|
||||
return batch_norm_layer(
|
||||
name=name + "_bn",
|
||||
input=tmp,
|
||||
act=active_type,
|
||||
use_global_stats=is_infer)
|
||||
|
||||
|
||||
def bottleneck_block(name, input, num_filters1, num_filters2):
|
||||
"""
|
||||
A wrapper for bottlenect building block in ResNet.
|
||||
Last conv_bn_layer has no activation.
|
||||
Addto layer has activation of relu.
|
||||
"""
|
||||
last_name = conv_bn_layer(
|
||||
name=name + '_branch2a',
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_filters=num_filters1,
|
||||
stride=1,
|
||||
padding=0)
|
||||
last_name = conv_bn_layer(
|
||||
name=name + '_branch2b',
|
||||
input=last_name,
|
||||
filter_size=3,
|
||||
num_filters=num_filters1,
|
||||
stride=1,
|
||||
padding=1)
|
||||
last_name = conv_bn_layer(
|
||||
name=name + '_branch2c',
|
||||
input=last_name,
|
||||
filter_size=1,
|
||||
num_filters=num_filters2,
|
||||
stride=1,
|
||||
padding=0,
|
||||
active_type=LinearActivation())
|
||||
|
||||
return addto_layer(
|
||||
name=name + "_addto", input=[input, last_name], act=ReluActivation())
|
||||
|
||||
|
||||
def mid_projection(name, input, num_filters1, num_filters2, stride=2):
|
||||
"""
|
||||
A wrapper for middile projection in ResNet.
|
||||
projection shortcuts are used for increasing dimensions,
|
||||
and other shortcuts are identity
|
||||
branch1: projection shortcuts are used for increasing
|
||||
dimensions, has no activation.
|
||||
branch2x: bottleneck building block, shortcuts are identity.
|
||||
"""
|
||||
# stride = 2
|
||||
branch1 = conv_bn_layer(
|
||||
name=name + '_branch1',
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_filters=num_filters2,
|
||||
stride=stride,
|
||||
padding=0,
|
||||
active_type=LinearActivation())
|
||||
|
||||
last_name = conv_bn_layer(
|
||||
name=name + '_branch2a',
|
||||
input=input,
|
||||
filter_size=1,
|
||||
num_filters=num_filters1,
|
||||
stride=stride,
|
||||
padding=0)
|
||||
last_name = conv_bn_layer(
|
||||
name=name + '_branch2b',
|
||||
input=last_name,
|
||||
filter_size=3,
|
||||
num_filters=num_filters1,
|
||||
stride=1,
|
||||
padding=1)
|
||||
|
||||
last_name = conv_bn_layer(
|
||||
name=name + '_branch2c',
|
||||
input=last_name,
|
||||
filter_size=1,
|
||||
num_filters=num_filters2,
|
||||
stride=1,
|
||||
padding=0,
|
||||
active_type=LinearActivation())
|
||||
|
||||
return addto_layer(
|
||||
name=name + "_addto", input=[branch1, last_name], act=ReluActivation())
|
||||
|
||||
|
||||
img = data_layer(name='image', size=height * width * 3)
|
||||
|
||||
|
||||
def deep_res_net(res2_num=3, res3_num=4, res4_num=6, res5_num=3):
|
||||
"""
|
||||
A wrapper for 50,101,152 layers of ResNet.
|
||||
res2_num: number of blocks stacked in conv2_x
|
||||
res3_num: number of blocks stacked in conv3_x
|
||||
res4_num: number of blocks stacked in conv4_x
|
||||
res5_num: number of blocks stacked in conv5_x
|
||||
"""
|
||||
# For ImageNet
|
||||
# conv1: 112x112
|
||||
tmp = conv_bn_layer(
|
||||
"conv1",
|
||||
input=img,
|
||||
filter_size=7,
|
||||
channels=3,
|
||||
num_filters=64,
|
||||
stride=2,
|
||||
padding=3)
|
||||
tmp = img_pool_layer(name="pool1", input=tmp, pool_size=3, stride=2)
|
||||
|
||||
# conv2_x: 56x56
|
||||
tmp = mid_projection(
|
||||
name="res2_1", input=tmp, num_filters1=64, num_filters2=256, stride=1)
|
||||
for i in xrange(2, res2_num + 1, 1):
|
||||
tmp = bottleneck_block(
|
||||
name="res2_" + str(i), input=tmp, num_filters1=64, num_filters2=256)
|
||||
|
||||
# conv3_x: 28x28
|
||||
tmp = mid_projection(
|
||||
name="res3_1", input=tmp, num_filters1=128, num_filters2=512)
|
||||
for i in xrange(2, res3_num + 1, 1):
|
||||
tmp = bottleneck_block(
|
||||
name="res3_" + str(i),
|
||||
input=tmp,
|
||||
num_filters1=128,
|
||||
num_filters2=512)
|
||||
|
||||
# conv4_x: 14x14
|
||||
tmp = mid_projection(
|
||||
name="res4_1", input=tmp, num_filters1=256, num_filters2=1024)
|
||||
for i in xrange(2, res4_num + 1, 1):
|
||||
tmp = bottleneck_block(
|
||||
name="res4_" + str(i),
|
||||
input=tmp,
|
||||
num_filters1=256,
|
||||
num_filters2=1024)
|
||||
|
||||
# conv5_x: 7x7
|
||||
tmp = mid_projection(
|
||||
name="res5_1", input=tmp, num_filters1=512, num_filters2=2048)
|
||||
for i in xrange(2, res5_num + 1, 1):
|
||||
tmp = bottleneck_block(
|
||||
name="res5_" + str(i),
|
||||
input=tmp,
|
||||
num_filters1=512,
|
||||
num_filters2=2048)
|
||||
|
||||
tmp = img_pool_layer(
|
||||
name='avgpool',
|
||||
input=tmp,
|
||||
pool_size=7,
|
||||
stride=1,
|
||||
pool_type=AvgPooling())
|
||||
|
||||
return fc_layer(input=tmp, size=num_class, act=SoftmaxActivation())
|
||||
|
||||
|
||||
if layer_num == 50:
|
||||
resnet = deep_res_net(3, 4, 6, 3)
|
||||
elif layer_num == 101:
|
||||
resnet = deep_res_net(3, 4, 23, 3)
|
||||
elif layer_num == 152:
|
||||
resnet = deep_res_net(3, 8, 36, 3)
|
||||
else:
|
||||
print("Wrong layer number.")
|
||||
|
||||
if is_infer:
|
||||
outputs(resnet)
|
||||
else:
|
||||
lbl = data_layer(name="label", size=num_class)
|
||||
loss = cross_entropy(name='loss', input=resnet, label=lbl)
|
||||
outputs(loss)
|
||||
@ -1,53 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
function train() {
|
||||
cfg=$1
|
||||
thread=$2
|
||||
bz=$3
|
||||
args="batch_size=$3"
|
||||
prefix=$4
|
||||
paddle train --job=time \
|
||||
--config=$cfg \
|
||||
--use_gpu=True \
|
||||
--trainer_count=$thread \
|
||||
--log_period=10 \
|
||||
--test_period=100 \
|
||||
--config_args=$args \
|
||||
> logs/$prefix-${thread}gpu-$bz.log 2>&1
|
||||
}
|
||||
|
||||
if [ ! -d "train.list" ]; then
|
||||
echo " " > train.list
|
||||
fi
|
||||
if [ ! -d "logs" ]; then
|
||||
mkdir logs
|
||||
fi
|
||||
|
||||
#========single-gpu=========#
|
||||
# alexnet
|
||||
train alexnet.py 1 64 alexnet
|
||||
train alexnet.py 1 128 alexnet
|
||||
train alexnet.py 1 256 alexnet
|
||||
train alexnet.py 1 512 alexnet
|
||||
|
||||
# googlenet
|
||||
train googlenet.py 1 64 googlenet
|
||||
train googlenet.py 1 128 googlenet
|
||||
train googlenet.py 1 256 googlenet
|
||||
|
||||
# smallnet
|
||||
train smallnet_mnist_cifar.py 1 64 smallnet
|
||||
train smallnet_mnist_cifar.py 1 128 smallnet
|
||||
train smallnet_mnist_cifar.py 1 256 smallnet
|
||||
train smallnet_mnist_cifar.py 1 512 smallnet
|
||||
|
||||
|
||||
############################
|
||||
#========multi-gpus=========#
|
||||
train alexnet.py 4 512 alexnet
|
||||
train alexnet.py 4 1024 alexnet
|
||||
|
||||
train googlenet.py 4 512 googlenet
|
||||
train googlenet.py 4 1024 googlenet
|
||||
@ -1,89 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
function clock_to_seconds() {
|
||||
hours=`echo $1 | awk -F ':' '{print $1}'`
|
||||
mins=`echo $1 | awk -F ':' '{print $2}'`
|
||||
secs=`echo $1 | awk -F ':' '{print $3}'`
|
||||
echo `awk 'BEGIN{printf "%.2f",('$secs' + '$mins' * 60 + '$hours' * 3600)}'`
|
||||
}
|
||||
|
||||
function infer() {
|
||||
unset OMP_NUM_THREADS MKL_NUM_THREADS OMP_DYNAMIC KMP_AFFINITY
|
||||
topology=$1
|
||||
layer_num=$2
|
||||
bs=$3
|
||||
use_mkldnn=$4
|
||||
if [ $4 == "True" ]; then
|
||||
thread=1
|
||||
log="logs/infer-${topology}-${layer_num}-mkldnn-${bs}.log"
|
||||
elif [ $4 == "False" ]; then
|
||||
thread=`nproc`
|
||||
if [ $thread -gt $bs ]; then
|
||||
thread=$bs
|
||||
fi
|
||||
log="logs/infer-${topology}-${layer_num}-${thread}mklml-${bs}.log"
|
||||
else
|
||||
echo "Wrong input $4, use True or False."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
models_in="models/${topology}-${layer_num}/pass-00000/"
|
||||
if [ ! -d $models_in ]; then
|
||||
echo "Training model ${topology}_${layer_num}"
|
||||
paddle train --job=train \
|
||||
--config="${topology}.py" \
|
||||
--use_mkldnn=True \
|
||||
--use_gpu=False \
|
||||
--trainer_count=1 \
|
||||
--num_passes=1 \
|
||||
--save_dir="models/${topology}-${layer_num}" \
|
||||
--config_args="batch_size=128,layer_num=${layer_num},num_samples=256" \
|
||||
> /dev/null 2>&1
|
||||
echo "Done"
|
||||
fi
|
||||
log_period=$((256 / bs))
|
||||
paddle train --job=test \
|
||||
--config="${topology}.py" \
|
||||
--use_mkldnn=$use_mkldnn \
|
||||
--use_gpu=False \
|
||||
--trainer_count=$thread \
|
||||
--log_period=$log_period \
|
||||
--config_args="batch_size=${bs},layer_num=${layer_num},is_infer=True" \
|
||||
--init_model_path=$models_in \
|
||||
2>&1 | tee ${log}
|
||||
|
||||
# calculate the last 5 logs period time of 1280 samples,
|
||||
# the time before are burning time.
|
||||
start=`tail ${log} -n 7 | head -n 1 | awk -F ' ' '{print $2}' | xargs`
|
||||
end=`tail ${log} -n 2 | head -n 1 | awk -F ' ' '{print $2}' | xargs`
|
||||
start_sec=`clock_to_seconds $start`
|
||||
end_sec=`clock_to_seconds $end`
|
||||
fps=`awk 'BEGIN{printf "%.2f",(1280 / ('$end_sec' - '$start_sec'))}'`
|
||||
echo "Last 1280 samples start: ${start}(${start_sec} sec), end: ${end}(${end_sec} sec;" >> ${log}
|
||||
echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
|
||||
}
|
||||
|
||||
if [ ! -f "train.list" ]; then
|
||||
echo " " > train.list
|
||||
fi
|
||||
if [ ! -f "test.list" ]; then
|
||||
echo " " > test.list
|
||||
fi
|
||||
if [ ! -d "logs" ]; then
|
||||
mkdir logs
|
||||
fi
|
||||
if [ ! -d "models" ]; then
|
||||
mkdir -p models
|
||||
fi
|
||||
|
||||
# inference benchmark
|
||||
for use_mkldnn in True False; do
|
||||
for batchsize in 1 2 4 8 16; do
|
||||
infer vgg 19 $batchsize $use_mkldnn
|
||||
infer resnet 50 $batchsize $use_mkldnn
|
||||
infer googlenet v1 $batchsize $use_mkldnn
|
||||
infer alexnet 2 $batchsize $use_mkldnn
|
||||
done
|
||||
done
|
||||
@ -1,54 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
function train() {
|
||||
unset OMP_NUM_THREADS MKL_NUM_THREADS OMP_DYNAMIC KMP_AFFINITY
|
||||
topology=$1
|
||||
layer_num=$2
|
||||
bs=$3
|
||||
use_mkldnn=$4
|
||||
if [ $4 == "True" ]; then
|
||||
thread=1
|
||||
log="logs/train-${topology}-${layer_num}-mkldnn-${bs}.log"
|
||||
elif [ $4 == "False" ]; then
|
||||
thread=`nproc`
|
||||
# each trainer_count use only 1 core to avoid conflict
|
||||
log="logs/train-${topology}-${layer_num}-${thread}mklml-${bs}.log"
|
||||
else
|
||||
echo "Wrong input $4, use True or False."
|
||||
exit 0
|
||||
fi
|
||||
args="batch_size=${bs},layer_num=${layer_num}"
|
||||
config="${topology}.py"
|
||||
paddle train --job=time \
|
||||
--config=$config \
|
||||
--use_mkldnn=$use_mkldnn \
|
||||
--use_gpu=False \
|
||||
--trainer_count=$thread \
|
||||
--log_period=10 \
|
||||
--test_period=100 \
|
||||
--config_args=$args \
|
||||
2>&1 | tee ${log}
|
||||
|
||||
avg_time=`tail ${log} -n 1 | awk -F ' ' '{print $8}' | sed 's/avg=//'`
|
||||
fps=`awk 'BEGIN{printf "%.2f",('$bs' / '$avg_time' * 1000)}'`
|
||||
echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
|
||||
}
|
||||
|
||||
if [ ! -f "train.list" ]; then
|
||||
echo " " > train.list
|
||||
fi
|
||||
if [ ! -d "logs" ]; then
|
||||
mkdir logs
|
||||
fi
|
||||
|
||||
# training benchmark
|
||||
for use_mkldnn in True False; do
|
||||
for batchsize in 64 128 256; do
|
||||
train vgg 19 $batchsize $use_mkldnn
|
||||
train resnet 50 $batchsize $use_mkldnn
|
||||
train googlenet v1 $batchsize $use_mkldnn
|
||||
train alexnet 2 $batchsize $use_mkldnn
|
||||
done
|
||||
done
|
||||
@ -1,71 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
function clock_to_seconds() {
|
||||
hours=`echo $1 | awk -F ':' '{print $1}'`
|
||||
mins=`echo $1 | awk -F ':' '{print $2}'`
|
||||
secs=`echo $1 | awk -F ':' '{print $3}'`
|
||||
echo `awk 'BEGIN{printf "%.2f",('$secs' + '$mins' * 60 + '$hours' * 3600)}'`
|
||||
}
|
||||
|
||||
function infer() {
|
||||
export OPENBLAS_MAIN_FREE=1
|
||||
topology=$1
|
||||
layer_num=$2
|
||||
bs=$3
|
||||
trainers=`nproc`
|
||||
if [ $trainers -gt $bs ]; then
|
||||
trainers=$bs
|
||||
fi
|
||||
log="logs/infer-${topology}-${layer_num}-${trainers}openblas-${bs}.log"
|
||||
threads=$((`nproc` / trainers))
|
||||
if [ $threads -eq 0 ]; then
|
||||
threads=1
|
||||
fi
|
||||
export OPENBLAS_NUM_THREADS=$threads
|
||||
|
||||
models_in="models/${topology}-${layer_num}/pass-00000/"
|
||||
if [ ! -d $models_in ]; then
|
||||
echo "./run_mkl_infer.sh to save the model first"
|
||||
exit 0
|
||||
fi
|
||||
log_period=$((32 / bs))
|
||||
paddle train --job=test \
|
||||
--config="${topology}.py" \
|
||||
--use_mkldnn=False \
|
||||
--use_gpu=False \
|
||||
--trainer_count=$trainers \
|
||||
--log_period=$log_period \
|
||||
--config_args="batch_size=${bs},layer_num=${layer_num},is_infer=True,num_samples=256" \
|
||||
--init_model_path=$models_in \
|
||||
2>&1 | tee ${log}
|
||||
|
||||
# calculate the last 5 logs period time of 160(=32*5) samples,
|
||||
# the time before are burning time.
|
||||
start=`tail ${log} -n 7 | head -n 1 | awk -F ' ' '{print $2}' | xargs`
|
||||
end=`tail ${log} -n 2 | head -n 1 | awk -F ' ' '{print $2}' | xargs`
|
||||
start_sec=`clock_to_seconds $start`
|
||||
end_sec=`clock_to_seconds $end`
|
||||
fps=`awk 'BEGIN{printf "%.2f",(160 / ('$end_sec' - '$start_sec'))}'`
|
||||
echo "Last 160 samples start: ${start}(${start_sec} sec), end: ${end}(${end_sec} sec;" >> ${log}
|
||||
echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
|
||||
}
|
||||
|
||||
if [ ! -f "train.list" ]; then
|
||||
echo " " > train.list
|
||||
fi
|
||||
if [ ! -f "test.list" ]; then
|
||||
echo " " > test.list
|
||||
fi
|
||||
if [ ! -d "logs" ]; then
|
||||
mkdir logs
|
||||
fi
|
||||
|
||||
# inference benchmark
|
||||
for batchsize in 1 2 4 8 16; do
|
||||
infer vgg 19 $batchsize
|
||||
infer resnet 50 $batchsize
|
||||
infer googlenet v1 $batchsize
|
||||
infer alexnet 2 $batchsize
|
||||
done
|
||||
@ -1,43 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
function train() {
|
||||
export OPENBLAS_NUM_THREADS=1
|
||||
topology=$1
|
||||
layer_num=$2
|
||||
bs=$3
|
||||
thread=`nproc`
|
||||
# each trainer_count use only 1 core to avoid conflict
|
||||
log="logs/train-${topology}-${layer_num}-${thread}openblas-${bs}.log"
|
||||
args="batch_size=${bs},layer_num=${layer_num}"
|
||||
config="${topology}.py"
|
||||
paddle train --job=time \
|
||||
--config=$config \
|
||||
--use_mkldnn=False \
|
||||
--use_gpu=False \
|
||||
--trainer_count=$thread \
|
||||
--log_period=3 \
|
||||
--test_period=30 \
|
||||
--config_args=$args \
|
||||
2>&1 | tee ${log}
|
||||
|
||||
avg_time=`tail ${log} -n 1 | awk -F ' ' '{print $8}' | sed 's/avg=//'`
|
||||
fps=`awk 'BEGIN{printf "%.2f",('$bs' / '$avg_time' * 1000)}'`
|
||||
echo "FPS: $fps images/sec" 2>&1 | tee -a ${log}
|
||||
}
|
||||
|
||||
if [ ! -f "train.list" ]; then
|
||||
echo " " > train.list
|
||||
fi
|
||||
if [ ! -d "logs" ]; then
|
||||
mkdir logs
|
||||
fi
|
||||
|
||||
# training benchmark
|
||||
for batchsize in 64 128 256; do
|
||||
train vgg 19 $batchsize
|
||||
train resnet 50 $batchsize
|
||||
train googlenet v1 $batchsize
|
||||
train alexnet 2 $batchsize
|
||||
done
|
||||
@ -1,49 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
from paddle.trainer_config_helpers import *
|
||||
|
||||
height = 32
|
||||
width = 32
|
||||
num_class = 10
|
||||
|
||||
batch_size = get_config_arg('batch_size', int, 128)
|
||||
|
||||
args = {'height': height, 'width': width, 'color': True, 'num_class': num_class}
|
||||
define_py_data_sources2(
|
||||
"train.list", None, module="provider", obj="process", args=args)
|
||||
|
||||
settings(
|
||||
batch_size=batch_size,
|
||||
learning_rate=0.01 / batch_size,
|
||||
learning_method=MomentumOptimizer(0.9),
|
||||
regularization=L2Regularization(0.0005 * batch_size))
|
||||
|
||||
# conv1
|
||||
net = data_layer('data', size=height * width * 3)
|
||||
net = img_conv_layer(
|
||||
input=net,
|
||||
filter_size=5,
|
||||
num_channels=3,
|
||||
num_filters=32,
|
||||
stride=1,
|
||||
padding=2)
|
||||
net = img_pool_layer(input=net, pool_size=3, stride=2, padding=1)
|
||||
|
||||
# conv2
|
||||
net = img_conv_layer(
|
||||
input=net, filter_size=5, num_filters=32, stride=1, padding=2)
|
||||
net = img_pool_layer(
|
||||
input=net, pool_size=3, stride=2, padding=1, pool_type=AvgPooling())
|
||||
|
||||
# conv3
|
||||
net = img_conv_layer(
|
||||
input=net, filter_size=3, num_filters=64, stride=1, padding=1)
|
||||
net = img_pool_layer(
|
||||
input=net, pool_size=3, stride=2, padding=1, pool_type=AvgPooling())
|
||||
|
||||
net = fc_layer(input=net, size=64, act=ReluActivation())
|
||||
net = fc_layer(input=net, size=10, act=SoftmaxActivation())
|
||||
|
||||
lab = data_layer('label', num_class)
|
||||
loss = classification_cost(input=net, label=lab)
|
||||
outputs(loss)
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue