Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into seq_error
wanghaoshuang
7 years ago
commit
7ff3855d8c
@ -0,0 +1,18 @@
|
|||||||
|
#FROM python:2.7.14
|
||||||
|
FROM nvidia/cuda:8.0-cudnn5-runtime-ubuntu16.04
|
||||||
|
RUN apt-get update && apt-get install -y python
|
||||||
|
RUN pip install -U kubernetes opencv-python && apt-get update -y && apt-get install -y iputils-ping libgtk2.0-dev
|
||||||
|
# NOTE: By default CI built wheel packages turn WITH_DISTRIBUTE=OFF,
|
||||||
|
# so we must build one with distribute support to install in this image.
|
||||||
|
RUN pip install paddlepaddle
|
||||||
|
RUN sh -c 'echo "import paddle.v2 as paddle\npaddle.dataset.cifar.train10()" | python'
|
||||||
|
RUN pip uninstall -y paddlepaddle
|
||||||
|
|
||||||
|
# below lines may change a lot for debugging
|
||||||
|
ADD https://raw.githubusercontent.com/PaddlePaddle/cloud/develop/docker/paddle_k8s /usr/bin
|
||||||
|
ADD https://raw.githubusercontent.com/PaddlePaddle/cloud/develop/docker/k8s_tools.py /root
|
||||||
|
ADD *.whl /
|
||||||
|
RUN pip install /*.whl && rm -f /*.whl && \
|
||||||
|
chmod +x /usr/bin/paddle_k8s
|
||||||
|
ENV LD_LIBRARY_PATH=/usr/local/lib
|
||||||
|
ADD vgg16_fluid.py vgg16_v2.py /workspace/
|
||||||
@ -0,0 +1,76 @@
|
|||||||
|
# Performance for Distributed vgg16
|
||||||
|
|
||||||
|
## Test Result
|
||||||
|
|
||||||
|
### Hardware Infomation
|
||||||
|
|
||||||
|
- CPU: Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
|
||||||
|
- cpu MHz : 2101.000
|
||||||
|
- cache size : 20480 KB
|
||||||
|
|
||||||
|
### Single Node Single Thread
|
||||||
|
|
||||||
|
- PServer Count: 10
|
||||||
|
- Trainer Count: 20
|
||||||
|
- Metrics: samples / sec
|
||||||
|
|
||||||
|
| Batch Size | 32 | 64 | 128 | 256 |
|
||||||
|
| -- | -- | -- | -- | -- |
|
||||||
|
| PaddlePaddle Fluid | 15.44 | 16.32 | 16.74 | 16.79 |
|
||||||
|
| PaddlePaddle v2 | 15.97 | 17.04 | 17.60 | 17.83 |
|
||||||
|
| TensorFlow | - | - | - | - |
|
||||||
|
|
||||||
|
### Different Batch Size
|
||||||
|
|
||||||
|
- PServer Count: 10
|
||||||
|
- Trainer Count: 20
|
||||||
|
- Per trainer CPU Core: 1
|
||||||
|
- Metrics: samples / sec
|
||||||
|
|
||||||
|
| Batch Size | 32 | 64 | 128 | 256 |
|
||||||
|
| -- | -- | -- | -- | -- |
|
||||||
|
| PaddlePaddle Fluid | 190.20 | 222.15 | 247.40 | 258.18 |
|
||||||
|
| PaddlePaddle v2 | 170.96 | 233.71 | 256.14 | 329.23 |
|
||||||
|
| TensorFlow | - | - | - | - |
|
||||||
|
|
||||||
|
|
||||||
|
### Accelerate Rate
|
||||||
|
|
||||||
|
- Pserver Count: 20
|
||||||
|
- Batch Size: 128
|
||||||
|
- Metrics: samples / sec
|
||||||
|
|
||||||
|
| Trainer Count | 20 | 40 | 80 | 100 |
|
||||||
|
| -- | -- | -- | -- | -- |
|
||||||
|
| PaddlePaddle Fluid | 263.29 (78.64%) | 518.80 (77.47%) | 836.26 (62.44%) | 1019.29 (60.89%) |
|
||||||
|
| PaddlePaddle v2 (need more tests) | 326.85 (92.85%) | 534.58 (75.93%) | 853.30 (60.60%) | 1041.99 (59.20%) |
|
||||||
|
| TensorFlow | - | - | - | - |
|
||||||
|
|
||||||
|
### Different Pserver Count
|
||||||
|
|
||||||
|
- Trainer Count: 60
|
||||||
|
- Batch Size: 128
|
||||||
|
- Metrics: samples/ sec
|
||||||
|
|
||||||
|
| PServer Count | 3 | 6 |10 | 20 |
|
||||||
|
| -- | -- | -- | -- | -- |
|
||||||
|
| PaddlePaddle Fluid(should fix in next PR) | 589.1 | 592.6 | 656.4 | 655.8 |
|
||||||
|
| PaddlePaddle v2 | 593.4 | 791.3 | 729.7 | 821.7 |
|
||||||
|
| TensorFlow | - | - | - | - |
|
||||||
|
|
||||||
|
*The performance gap between Fuild and v2 comes from the network interference.*
|
||||||
|
|
||||||
|
|
||||||
|
## Steps to Run the Performance Test
|
||||||
|
|
||||||
|
1. You must re-compile PaddlePaddle and enable `-DWITH_DISTRIBUTE` to build PaddlePaddle with distributed support.
|
||||||
|
1. When the build finishes, copy the output `whl` package located under `build/python/dist` to current directory.
|
||||||
|
1. Run `docker build -t [image:tag] .` to build the docker image and run `docker push [image:tag]` to push the image to reponsitory so kubernetes can find it.
|
||||||
|
1. Run `kubectl create -f pserver.yaml && kubectl create -f trainer.yaml` to start the job on your kubernetes cluster (you must configure the `kubectl` client before this step).
|
||||||
|
1. Run `kubectl get po` to get running pods, and run `kubectl logs [podID]` to fetch the pod log of pservers and trainers.
|
||||||
|
|
||||||
|
Check the logs for the distributed training progress and analyze the performance.
|
||||||
|
|
||||||
|
## Enable Verbos Logs
|
||||||
|
|
||||||
|
Edit `pserver.yaml` and `trainer.yaml` and add an environment variable `GLOG_v=3` and `GLOG_logtostderr=1` to see what happend in detail.
|
||||||
@ -0,0 +1,72 @@
|
|||||||
|
apiVersion: extensions/v1beta1
|
||||||
|
kind: ReplicaSet
|
||||||
|
metadata:
|
||||||
|
name: vgg16job-pserver
|
||||||
|
spec:
|
||||||
|
replicas: 10
|
||||||
|
template:
|
||||||
|
metadata:
|
||||||
|
labels:
|
||||||
|
paddle-job-pserver: vgg16job
|
||||||
|
spec:
|
||||||
|
hostNetwork: true
|
||||||
|
imagePullSecrets:
|
||||||
|
- name: job-registry-secret
|
||||||
|
containers:
|
||||||
|
- name: pserver
|
||||||
|
image: "registry.baidu.com/paddlepaddle/fluid_benchmark:vgg16"
|
||||||
|
imagePullPolicy: Always
|
||||||
|
ports:
|
||||||
|
- name: jobport-30236
|
||||||
|
containerPort: 30236
|
||||||
|
env:
|
||||||
|
- name: PADDLE_JOB_NAME
|
||||||
|
value: vgg16job
|
||||||
|
- name: MKL_NUM_THREADS
|
||||||
|
value: "1"
|
||||||
|
- name: TRAINING_ROLE
|
||||||
|
value: "PSERVER"
|
||||||
|
- name: TRAINERS
|
||||||
|
value: "20"
|
||||||
|
- name: PSERVERS
|
||||||
|
value: "10"
|
||||||
|
- name: TOPOLOGY
|
||||||
|
value: ""
|
||||||
|
- name: ENTRY
|
||||||
|
value: "MKL_NUM_THREADS=1 python /workspace/vgg16_fluid.py --local 0"
|
||||||
|
- name: TRAINER_PACKAGE
|
||||||
|
value: "/workspace"
|
||||||
|
- name: PADDLE_INIT_PORT
|
||||||
|
value: "30236"
|
||||||
|
- name: PADDLE_INIT_NICS
|
||||||
|
value: "xgbe0"
|
||||||
|
- name: PADDLE_INIT_TRAINER_COUNT
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM_FOR_SPARSE
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_NUM_GRADIENT_SERVERS
|
||||||
|
value: "20"
|
||||||
|
- name: PADDLE_INIT_NUM_PASSES
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_USE_GPU
|
||||||
|
value: "0"
|
||||||
|
- name: LD_LIBRARY_PATH
|
||||||
|
value: "/usr/local/lib:/usr/local/nvidia/lib64"
|
||||||
|
- name: NAMESPACE
|
||||||
|
valueFrom:
|
||||||
|
fieldRef:
|
||||||
|
fieldPath: "metadata.namespace"
|
||||||
|
- name: POD_IP
|
||||||
|
valueFrom:
|
||||||
|
fieldRef:
|
||||||
|
fieldPath: "status.podIP"
|
||||||
|
command: ["paddle_k8s", "start_fluid"]
|
||||||
|
resources:
|
||||||
|
requests:
|
||||||
|
memory: 10Gi
|
||||||
|
cpu: 4
|
||||||
|
limits:
|
||||||
|
memory: 10Gi
|
||||||
|
cpu: 4
|
||||||
@ -0,0 +1,69 @@
|
|||||||
|
apiVersion: batch/v1
|
||||||
|
kind: Job
|
||||||
|
metadata:
|
||||||
|
name: vgg16job-trainer
|
||||||
|
spec:
|
||||||
|
parallelism: 20
|
||||||
|
completions: 20
|
||||||
|
template:
|
||||||
|
metadata:
|
||||||
|
labels:
|
||||||
|
paddle-job: vgg16job
|
||||||
|
spec:
|
||||||
|
imagePullSecrets:
|
||||||
|
- name: job-registry-secret
|
||||||
|
hostNetwork: true
|
||||||
|
containers:
|
||||||
|
- name: trainer
|
||||||
|
image: "registry.baidu.com/paddlepaddle/fluid_benchmark:vgg16"
|
||||||
|
imagePullPolicy: Always
|
||||||
|
command: ["paddle_k8s", "start_fluid"]
|
||||||
|
env:
|
||||||
|
- name: PADDLE_JOB_NAME
|
||||||
|
value: vgg16job
|
||||||
|
- name: TRAINING_ROLE
|
||||||
|
value: "TRAINER"
|
||||||
|
- name: TRAINERS
|
||||||
|
value: "20"
|
||||||
|
- name: PSERVERS
|
||||||
|
value: "10"
|
||||||
|
- name: TOPOLOGY
|
||||||
|
value: ""
|
||||||
|
- name: ENTRY
|
||||||
|
value: "MKL_NUM_THREADS=1 python /workspace/vgg16_fluid.py --local 0 --batch_size 128"
|
||||||
|
- name: TRAINER_PACKAGE
|
||||||
|
value: "/workspace"
|
||||||
|
- name: PADDLE_INIT_PORT
|
||||||
|
value: "30236"
|
||||||
|
- name: PADDLE_INIT_NICS
|
||||||
|
value: "xgbe0"
|
||||||
|
- name: PADDLE_INIT_TRAINER_COUNT
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM_FOR_SPARSE
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_NUM_GRADIENT_SERVERS
|
||||||
|
value: "20"
|
||||||
|
- name: PADDLE_INIT_NUM_PASSES
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_USE_GPU
|
||||||
|
value: "0"
|
||||||
|
- name: LD_LIBRARY_PATH
|
||||||
|
value: "/usr/local/lib:/usr/local/nvidia/lib64"
|
||||||
|
- name: NAMESPACE
|
||||||
|
valueFrom:
|
||||||
|
fieldRef:
|
||||||
|
fieldPath: "metadata.namespace"
|
||||||
|
- name: POD_IP
|
||||||
|
valueFrom:
|
||||||
|
fieldRef:
|
||||||
|
fieldPath: "status.podIP"
|
||||||
|
resources:
|
||||||
|
requests:
|
||||||
|
memory: 40Gi
|
||||||
|
cpu: 2
|
||||||
|
limits:
|
||||||
|
memory: 40Gi
|
||||||
|
cpu: 2
|
||||||
|
restartPolicy: Never
|
||||||
@ -0,0 +1,64 @@
|
|||||||
|
apiVersion: extensions/v1beta1
|
||||||
|
kind: ReplicaSet
|
||||||
|
metadata:
|
||||||
|
name: vgg16v2job-pserver
|
||||||
|
spec:
|
||||||
|
replicas: 10
|
||||||
|
template:
|
||||||
|
metadata:
|
||||||
|
labels:
|
||||||
|
paddle-job-pserver: vgg16v2job
|
||||||
|
spec:
|
||||||
|
hostNetwork: true
|
||||||
|
imagePullSecrets:
|
||||||
|
- name: job-registry-secret
|
||||||
|
containers:
|
||||||
|
- name: pserver
|
||||||
|
image: "registry.baidu.com/paddlepaddle/fluid_benchmark:vgg16"
|
||||||
|
imagePullPolicy: Always
|
||||||
|
ports:
|
||||||
|
- name: jobport-30236
|
||||||
|
containerPort: 30236
|
||||||
|
env:
|
||||||
|
- name: PADDLE_JOB_NAME
|
||||||
|
value: vgg16v2job
|
||||||
|
- name: TRAINERS
|
||||||
|
value: "20"
|
||||||
|
- name: PSERVERS
|
||||||
|
value: "10"
|
||||||
|
- name: TOPOLOGY
|
||||||
|
value: ""
|
||||||
|
- name: ENTRY
|
||||||
|
value: "python train.py"
|
||||||
|
- name: TRAINER_PACKAGE
|
||||||
|
value: "/workspace"
|
||||||
|
- name: PADDLE_INIT_PORT
|
||||||
|
value: "30236"
|
||||||
|
- name: PADDLE_INIT_NICS
|
||||||
|
value: "xgbe0"
|
||||||
|
- name: PADDLE_INIT_TRAINER_COUNT
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM_FOR_SPARSE
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_NUM_GRADIENT_SERVERS
|
||||||
|
value: "20"
|
||||||
|
- name: PADDLE_INIT_NUM_PASSES
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_USE_GPU
|
||||||
|
value: "0"
|
||||||
|
- name: LD_LIBRARY_PATH
|
||||||
|
value: "/usr/local/lib:/usr/local/nvidia/lib64"
|
||||||
|
- name: NAMESPACE
|
||||||
|
valueFrom:
|
||||||
|
fieldRef:
|
||||||
|
fieldPath: "metadata.namespace"
|
||||||
|
command: ["paddle_k8s", "start_pserver"]
|
||||||
|
resources:
|
||||||
|
requests:
|
||||||
|
memory: 10Gi
|
||||||
|
cpu: 4
|
||||||
|
limits:
|
||||||
|
memory: 10Gi
|
||||||
|
cpu: 4
|
||||||
@ -0,0 +1,65 @@
|
|||||||
|
apiVersion: batch/v1
|
||||||
|
kind: Job
|
||||||
|
metadata:
|
||||||
|
name: vgg16v2job-trainer
|
||||||
|
spec:
|
||||||
|
parallelism: 20
|
||||||
|
completions: 20
|
||||||
|
template:
|
||||||
|
metadata:
|
||||||
|
labels:
|
||||||
|
paddle-job: vgg16v2job
|
||||||
|
spec:
|
||||||
|
imagePullSecrets:
|
||||||
|
- name: job-registry-secret
|
||||||
|
hostNetwork: true
|
||||||
|
containers:
|
||||||
|
- name: trainer
|
||||||
|
image: "registry.baidu.com/paddlepaddle/fluid_benchmark:vgg16"
|
||||||
|
imagePullPolicy: Always
|
||||||
|
command: ["paddle_k8s", "start_trainer", "v2"]
|
||||||
|
env:
|
||||||
|
- name: PADDLE_JOB_NAME
|
||||||
|
value: vgg16v2job
|
||||||
|
- name: BATCH_SIZE
|
||||||
|
value: "256"
|
||||||
|
- name: TRAINERS
|
||||||
|
value: "20"
|
||||||
|
- name: PSERVERS
|
||||||
|
value: "10"
|
||||||
|
- name: TOPOLOGY
|
||||||
|
value: ""
|
||||||
|
- name: ENTRY
|
||||||
|
value: "cd /workspace && MKL_NUM_THREADS=1 python /workspace/vgg16_v2.py"
|
||||||
|
- name: TRAINER_PACKAGE
|
||||||
|
value: "/workspace"
|
||||||
|
- name: PADDLE_INIT_PORT
|
||||||
|
value: "30236"
|
||||||
|
- name: PADDLE_INIT_NICS
|
||||||
|
value: "xgbe0"
|
||||||
|
- name: PADDLE_INIT_TRAINER_COUNT
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_PORTS_NUM_FOR_SPARSE
|
||||||
|
value: "1"
|
||||||
|
- name: PADDLE_INIT_NUM_GRADIENT_SERVERS
|
||||||
|
value: "20"
|
||||||
|
- name: PADDLE_INIT_NUM_PASSES
|
||||||
|
value: "2"
|
||||||
|
- name: PADDLE_INIT_USE_GPU
|
||||||
|
value: "0"
|
||||||
|
- name: LD_LIBRARY_PATH
|
||||||
|
value: "/usr/local/lib:/usr/local/nvidia/lib64"
|
||||||
|
- name: NAMESPACE
|
||||||
|
valueFrom:
|
||||||
|
fieldRef:
|
||||||
|
fieldPath: "metadata.namespace"
|
||||||
|
resources:
|
||||||
|
requests:
|
||||||
|
memory: 40Gi
|
||||||
|
cpu: 2
|
||||||
|
limits:
|
||||||
|
memory: 40Gi
|
||||||
|
cpu: 2
|
||||||
|
restartPolicy: Never
|
||||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,154 @@
|
|||||||
|
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserve.
|
||||||
|
#
|
||||||
|
#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 gzip
|
||||||
|
|
||||||
|
import paddle.v2.dataset.cifar as cifar
|
||||||
|
import paddle.v2 as paddle
|
||||||
|
import time
|
||||||
|
import os
|
||||||
|
|
||||||
|
DATA_DIM = 3 * 32 * 32
|
||||||
|
CLASS_DIM = 10
|
||||||
|
BATCH_SIZE = os.getenv("BATCH_SIZE")
|
||||||
|
if BATCH_SIZE:
|
||||||
|
BATCH_SIZE = int(BATCH_SIZE)
|
||||||
|
else:
|
||||||
|
BATCH_SIZE = 128
|
||||||
|
print "batch_size", BATCH_SIZE
|
||||||
|
NODE_COUNT = int(os.getenv("TRAINERS"))
|
||||||
|
ts = 0
|
||||||
|
|
||||||
|
|
||||||
|
def vgg(input, nums, class_dim):
|
||||||
|
def conv_block(input, num_filter, groups, num_channels=None):
|
||||||
|
return paddle.networks.img_conv_group(
|
||||||
|
input=input,
|
||||||
|
num_channels=num_channels,
|
||||||
|
pool_size=2,
|
||||||
|
pool_stride=2,
|
||||||
|
conv_num_filter=[num_filter] * groups,
|
||||||
|
conv_filter_size=3,
|
||||||
|
conv_act=paddle.activation.Relu(),
|
||||||
|
pool_type=paddle.pooling.Max())
|
||||||
|
|
||||||
|
assert len(nums) == 5
|
||||||
|
# the channel of input feature is 3
|
||||||
|
conv1 = conv_block(input, 64, nums[0], 3)
|
||||||
|
conv2 = conv_block(conv1, 128, nums[1])
|
||||||
|
conv3 = conv_block(conv2, 256, nums[2])
|
||||||
|
conv4 = conv_block(conv3, 512, nums[3])
|
||||||
|
conv5 = conv_block(conv4, 512, nums[4])
|
||||||
|
|
||||||
|
fc_dim = 512
|
||||||
|
fc1 = paddle.layer.fc(input=conv5,
|
||||||
|
size=fc_dim,
|
||||||
|
act=paddle.activation.Relu(),
|
||||||
|
layer_attr=paddle.attr.Extra(drop_rate=0.5))
|
||||||
|
fc2 = paddle.layer.fc(input=fc1,
|
||||||
|
size=fc_dim,
|
||||||
|
act=paddle.activation.Relu(),
|
||||||
|
layer_attr=paddle.attr.Extra(drop_rate=0.5))
|
||||||
|
out = paddle.layer.fc(input=fc2,
|
||||||
|
size=class_dim,
|
||||||
|
act=paddle.activation.Softmax())
|
||||||
|
return out
|
||||||
|
|
||||||
|
|
||||||
|
def vgg13(input, class_dim):
|
||||||
|
nums = [2, 2, 2, 2, 2]
|
||||||
|
return vgg(input, nums, class_dim)
|
||||||
|
|
||||||
|
|
||||||
|
def vgg16(input, class_dim):
|
||||||
|
nums = [2, 2, 3, 3, 3]
|
||||||
|
return vgg(input, nums, class_dim)
|
||||||
|
|
||||||
|
|
||||||
|
def vgg19(input, class_dim):
|
||||||
|
nums = [2, 2, 4, 4, 4]
|
||||||
|
return vgg(input, nums, class_dim)
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
global ts
|
||||||
|
paddle.init(use_gpu=False)
|
||||||
|
image = paddle.layer.data(
|
||||||
|
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
|
||||||
|
lbl = paddle.layer.data(
|
||||||
|
name="label", type=paddle.data_type.integer_value(CLASS_DIM))
|
||||||
|
|
||||||
|
extra_layers = None
|
||||||
|
# NOTE: for v2 distributed training need averaging updates.
|
||||||
|
learning_rate = 1e-3 / NODE_COUNT
|
||||||
|
out = vgg16(image, class_dim=CLASS_DIM)
|
||||||
|
cost = paddle.layer.classification_cost(input=out, label=lbl)
|
||||||
|
|
||||||
|
# Create parameters
|
||||||
|
parameters = paddle.parameters.create(cost)
|
||||||
|
|
||||||
|
# Create optimizer
|
||||||
|
optimizer = paddle.optimizer.Momentum(
|
||||||
|
momentum=0.9,
|
||||||
|
regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
|
||||||
|
BATCH_SIZE),
|
||||||
|
learning_rate=learning_rate / BATCH_SIZE,
|
||||||
|
learning_rate_decay_a=0.1,
|
||||||
|
learning_rate_decay_b=128000 * 35,
|
||||||
|
learning_rate_schedule="discexp", )
|
||||||
|
|
||||||
|
train_reader = paddle.batch(
|
||||||
|
paddle.reader.shuffle(
|
||||||
|
cifar.train10(),
|
||||||
|
# To use other data, replace the above line with:
|
||||||
|
# reader.train_reader('train.list'),
|
||||||
|
buf_size=1000),
|
||||||
|
batch_size=BATCH_SIZE)
|
||||||
|
test_reader = paddle.batch(
|
||||||
|
cifar.test10(),
|
||||||
|
# To use other data, replace the above line with:
|
||||||
|
# reader.test_reader('val.list'),
|
||||||
|
batch_size=BATCH_SIZE)
|
||||||
|
|
||||||
|
# Create trainer
|
||||||
|
trainer = paddle.trainer.SGD(cost=cost,
|
||||||
|
parameters=parameters,
|
||||||
|
update_equation=optimizer,
|
||||||
|
extra_layers=extra_layers,
|
||||||
|
is_local=False)
|
||||||
|
|
||||||
|
# End batch and end pass event handler
|
||||||
|
def event_handler(event):
|
||||||
|
global ts, ts_pass
|
||||||
|
if isinstance(event, paddle.event.BeginPass):
|
||||||
|
ts_pass = time.time()
|
||||||
|
if isinstance(event, paddle.event.BeginIteration):
|
||||||
|
ts = time.time()
|
||||||
|
if isinstance(event, paddle.event.EndIteration):
|
||||||
|
if event.batch_id % 1 == 0:
|
||||||
|
print "\nPass %d, Batch %d, Cost %f, %s, spent: %f" % (
|
||||||
|
event.pass_id, event.batch_id, event.cost, event.metrics,
|
||||||
|
time.time() - ts)
|
||||||
|
if isinstance(event, paddle.event.EndPass):
|
||||||
|
print "Pass %d end, spent: %f" % (event.pass_id,
|
||||||
|
time.time() - ts_pass)
|
||||||
|
result = trainer.test(reader=test_reader)
|
||||||
|
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
|
||||||
|
|
||||||
|
trainer.train(
|
||||||
|
reader=train_reader, num_passes=200, event_handler=event_handler)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == '__main__':
|
||||||
|
main()
|
||||||
@ -0,0 +1,90 @@
|
|||||||
|
# make package for paddle fluid shared and static library
|
||||||
|
function(copy TARGET)
|
||||||
|
set(options "")
|
||||||
|
set(oneValueArgs "")
|
||||||
|
set(multiValueArgs SRCS DSTS DEPS)
|
||||||
|
cmake_parse_arguments(copy_lib "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
|
||||||
|
|
||||||
|
list(LENGTH copy_lib_SRCS copy_lib_SRCS_len)
|
||||||
|
list(LENGTH copy_lib_DSTS copy_lib_DSTS_len)
|
||||||
|
if(NOT ${copy_lib_SRCS_len} EQUAL ${copy_lib_DSTS_len})
|
||||||
|
message(FATAL_ERROR "${TARGET} source numbers are not equal to destination numbers")
|
||||||
|
endif()
|
||||||
|
math(EXPR len "${copy_lib_SRCS_len} - 1")
|
||||||
|
|
||||||
|
add_custom_target(${TARGET} DEPENDS ${copy_lib_DEPS})
|
||||||
|
foreach(index RANGE ${len})
|
||||||
|
list(GET copy_lib_SRCS ${index} src)
|
||||||
|
list(GET copy_lib_DSTS ${index} dst)
|
||||||
|
add_custom_command(TARGET ${TARGET} PRE_BUILD COMMAND mkdir -p "${dst}")
|
||||||
|
if(IS_DIRECTORY ${src})
|
||||||
|
add_custom_command(TARGET ${TARGET} PRE_BUILD COMMAND cp -r "${src}" "${dst}")
|
||||||
|
else()
|
||||||
|
add_custom_command(TARGET ${TARGET} PRE_BUILD COMMAND cp "${src}" "${dst}")
|
||||||
|
endif()
|
||||||
|
endforeach()
|
||||||
|
endfunction()
|
||||||
|
|
||||||
|
# third party
|
||||||
|
set(dst_dir "${CMAKE_INSTALL_PREFIX}/third_party/eigen3")
|
||||||
|
copy(eigen3_lib
|
||||||
|
SRCS ${EIGEN_INCLUDE_DIR}/Eigen/Core ${EIGEN_INCLUDE_DIR}/Eigen/src ${EIGEN_INCLUDE_DIR}/unsupported/Eigen
|
||||||
|
DSTS ${dst_dir}/Eigen ${dst_dir}/Eigen ${dst_dir}/unsupported
|
||||||
|
)
|
||||||
|
|
||||||
|
set(dst_dir "${CMAKE_INSTALL_PREFIX}/third_party/install/gflags")
|
||||||
|
copy(gflags_lib
|
||||||
|
SRCS ${GFLAGS_INCLUDE_DIR} ${GFLAGS_LIBRARIES}
|
||||||
|
DSTS ${dst_dir} ${dst_dir}/lib
|
||||||
|
)
|
||||||
|
|
||||||
|
set(dst_dir "${CMAKE_INSTALL_PREFIX}/third_party/install/glog")
|
||||||
|
copy(glog_lib
|
||||||
|
SRCS ${GLOG_INCLUDE_DIR} ${GLOG_LIBRARIES}
|
||||||
|
DSTS ${dst_dir} ${dst_dir}/lib
|
||||||
|
)
|
||||||
|
|
||||||
|
IF(NOT PROTOBUF_FOUND)
|
||||||
|
set(dst_dir "${CMAKE_INSTALL_PREFIX}/third_party/install/protobuf")
|
||||||
|
copy(protobuf_lib
|
||||||
|
SRCS ${PROTOBUF_INCLUDE_DIR} ${PROTOBUF_LITE_LIBRARY}
|
||||||
|
DSTS ${dst_dir} ${dst_dir}/lib
|
||||||
|
)
|
||||||
|
ENDIF(NOT PROTOBUF_FOUND)
|
||||||
|
|
||||||
|
# paddle fluid module
|
||||||
|
set(src_dir "${PADDLE_SOURCE_DIR}/paddle")
|
||||||
|
set(dst_dir "${CMAKE_INSTALL_PREFIX}/paddle")
|
||||||
|
set(module "framework")
|
||||||
|
copy(framework_lib DEPS framework_py_proto
|
||||||
|
SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/details/*.h ${PADDLE_BINARY_DIR}/paddle/framework/framework.pb.h
|
||||||
|
DSTS ${dst_dir}/${module} ${dst_dir}/${module}/details ${dst_dir}/${module}
|
||||||
|
)
|
||||||
|
|
||||||
|
set(module "memory")
|
||||||
|
copy(memory_lib
|
||||||
|
SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/detail/*.h
|
||||||
|
DSTS ${dst_dir}/${module} ${dst_dir}/${module}/detail
|
||||||
|
)
|
||||||
|
|
||||||
|
set(module "inference")
|
||||||
|
copy(inference_lib DEPENDS paddle_fluid_shared
|
||||||
|
SRCS ${src_dir}/${module}/*.h ${PADDLE_BINARY_DIR}/paddle/inference/libpaddle_fluid.so
|
||||||
|
DSTS ${dst_dir}/${module} ${dst_dir}/${module}
|
||||||
|
)
|
||||||
|
|
||||||
|
set(module "platform")
|
||||||
|
copy(platform_lib
|
||||||
|
SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/dynload/*.h ${src_dir}/${module}/details/*.h
|
||||||
|
DSTS ${dst_dir}/${module} ${dst_dir}/${module}/dynload ${dst_dir}/${module}/details
|
||||||
|
)
|
||||||
|
|
||||||
|
set(module "string")
|
||||||
|
copy(string_lib
|
||||||
|
SRCS ${src_dir}/${module}/*.h ${src_dir}/${module}/tinyformat/*.h
|
||||||
|
DSTS ${dst_dir}/${module} ${dst_dir}/${module}/tinyformat
|
||||||
|
)
|
||||||
|
|
||||||
|
add_custom_target(inference_lib_dist DEPENDS
|
||||||
|
inference_lib framework_lib memory_lib platform_lib string_lib
|
||||||
|
gflags_lib glog_lib protobuf_lib eigen3_lib)
|
||||||
@ -0,0 +1,20 @@
|
|||||||
|
# configured documentation tools and intermediate build results
|
||||||
|
set(BINARY_BUILD_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/_build")
|
||||||
|
|
||||||
|
# Sphinx cache with pickled ReST documents
|
||||||
|
set(SPHINX_CACHE_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/_doctrees")
|
||||||
|
|
||||||
|
# HTML output director
|
||||||
|
set(SPHINX_HTML_DIR_EN "${CMAKE_CURRENT_BINARY_DIR}/en/html")
|
||||||
|
|
||||||
|
configure_file(
|
||||||
|
"${CMAKE_CURRENT_SOURCE_DIR}/../templates/conf.py.en.in"
|
||||||
|
"${BINARY_BUILD_DIR_EN}/conf.py"
|
||||||
|
@ONLY)
|
||||||
|
|
||||||
|
sphinx_add_target(paddle_api_docs
|
||||||
|
html
|
||||||
|
${BINARY_BUILD_DIR_EN}
|
||||||
|
${SPHINX_CACHE_DIR_EN}
|
||||||
|
${CMAKE_CURRENT_SOURCE_DIR}
|
||||||
|
${SPHINX_HTML_DIR_EN})
|
||||||
@ -1,9 +1,14 @@
|
|||||||
|
.. THIS FILE IS GENERATED BY `gen_doc.{py|sh}`
|
||||||
|
!DO NOT EDIT THIS FILE MANUALLY!
|
||||||
|
|
||||||
===========
|
===========
|
||||||
DataFeeder
|
data_feeder
|
||||||
===========
|
===========
|
||||||
|
|
||||||
DataFeeder
|
DataFeeder
|
||||||
-----------
|
----------
|
||||||
.. automodule:: paddle.v2.fluid.data_feeder
|
|
||||||
:members: DataFeeder
|
.. autoclass:: paddle.v2.fluid.data_feeder.DataFeeder
|
||||||
|
:members:
|
||||||
:noindex:
|
:noindex:
|
||||||
|
|
||||||
|
|||||||
@ -1,9 +1,21 @@
|
|||||||
===========
|
.. THIS FILE IS GENERATED BY `gen_doc.{py|sh}`
|
||||||
Evaluator
|
!DO NOT EDIT THIS FILE MANUALLY!
|
||||||
===========
|
|
||||||
|
=========
|
||||||
Evaluator
|
evaluator
|
||||||
-----------
|
=========
|
||||||
.. automodule:: paddle.v2.fluid.evaluator
|
|
||||||
:members: Evaluator
|
Accuracy
|
||||||
|
--------
|
||||||
|
|
||||||
|
.. autoclass:: paddle.v2.fluid.evaluator.Accuracy
|
||||||
|
:members:
|
||||||
:noindex:
|
:noindex:
|
||||||
|
|
||||||
|
ChunkEvaluator
|
||||||
|
--------------
|
||||||
|
|
||||||
|
.. autoclass:: paddle.v2.fluid.evaluator.ChunkEvaluator
|
||||||
|
:members:
|
||||||
|
:noindex:
|
||||||
|
|
||||||
|
|||||||
@ -1,9 +1,32 @@
|
|||||||
===========
|
.. THIS FILE IS GENERATED BY `gen_doc.{py|sh}`
|
||||||
Executor
|
!DO NOT EDIT THIS FILE MANUALLY!
|
||||||
===========
|
|
||||||
|
========
|
||||||
|
executor
|
||||||
|
========
|
||||||
|
|
||||||
Executor
|
Executor
|
||||||
|
--------
|
||||||
|
|
||||||
|
.. autoclass:: paddle.v2.fluid.executor.Executor
|
||||||
|
:members:
|
||||||
|
:noindex:
|
||||||
|
|
||||||
|
global_scope
|
||||||
|
------------
|
||||||
|
|
||||||
|
.. autofunction:: paddle.v2.fluid.executor.global_scope
|
||||||
|
:noindex:
|
||||||
|
|
||||||
|
scope_guard
|
||||||
-----------
|
-----------
|
||||||
.. automodule:: paddle.v2.fluid.executor
|
|
||||||
:members: Executor
|
.. autofunction:: paddle.v2.fluid.executor.scope_guard
|
||||||
|
:noindex:
|
||||||
|
|
||||||
|
switch_scope
|
||||||
|
------------
|
||||||
|
|
||||||
|
.. autofunction:: paddle.v2.fluid.executor.switch_scope
|
||||||
:noindex:
|
:noindex:
|
||||||
|
|
||||||
|
|||||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue