Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-ROIPooling-dev
guosheng
7 years ago
commit
1ffdecf1ac
@ -0,0 +1,15 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
readonly VERSION="3.8"
|
||||
|
||||
version=$(clang-format -version)
|
||||
|
||||
if ! [[ $version == *"$VERSION"* ]]; then
|
||||
echo "clang-format version check failed."
|
||||
echo "a version contains '$VERSION' is needed, but get '$version'"
|
||||
echo "you can install the right version, and make an soft-link to '\$PATH' env"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
clang-format $@
|
||||
@ -1 +1,157 @@
|
||||
./doc/howto/dev/contribute_to_paddle_en.md
|
||||
# Contribute Code
|
||||
|
||||
We sincerely appreciate your contribution. This document explains our workflow and work style.
|
||||
|
||||
## Workflow
|
||||
|
||||
PaddlePaddle uses this [Git branching model](http://nvie.com/posts/a-successful-git-branching-model/). The following steps guide usual contributions.
|
||||
|
||||
1. Fork
|
||||
|
||||
Our development community has been growing fastly; it doesn't make sense for everyone to write into the official repo. So, please file Pull Requests from your fork. To make a fork, just head over to the GitHub page and click the ["Fork" button](https://help.github.com/articles/fork-a-repo/).
|
||||
|
||||
1. Clone
|
||||
|
||||
To make a copy of your fork to your local computers, please run
|
||||
|
||||
```bash
|
||||
git clone https://github.com/your-github-account/paddle
|
||||
cd paddle
|
||||
```
|
||||
|
||||
1. Create the local feature branch
|
||||
|
||||
For daily works like adding a new feature or fixing a bug, please open your feature branch before coding:
|
||||
|
||||
```bash
|
||||
git checkout -b my-cool-stuff
|
||||
```
|
||||
|
||||
1. Commit
|
||||
|
||||
Before issuing your first `git commit` command, please install [`pre-commit`](http://pre-commit.com/) by running the following commands:
|
||||
|
||||
```bash
|
||||
pip install pre-commit
|
||||
pre-commit install
|
||||
```
|
||||
|
||||
Our pre-commit configuration requires clang-format 3.8 for auto-formating C/C++ code and yapf for Python.
|
||||
|
||||
Once installed, `pre-commit` checks the style of code and documentation in every commit. We will see something like the following when you run `git commit`:
|
||||
|
||||
```
|
||||
➜ git commit
|
||||
CRLF end-lines remover...............................(no files to check)Skipped
|
||||
yapf.................................................(no files to check)Skipped
|
||||
Check for added large files..............................................Passed
|
||||
Check for merge conflicts................................................Passed
|
||||
Check for broken symlinks................................................Passed
|
||||
Detect Private Key...................................(no files to check)Skipped
|
||||
Fix End of Files.....................................(no files to check)Skipped
|
||||
clang-formater.......................................(no files to check)Skipped
|
||||
[my-cool-stuff c703c041] add test file
|
||||
1 file changed, 0 insertions(+), 0 deletions(-)
|
||||
create mode 100644 233
|
||||
```
|
||||
|
||||
1. Build and test
|
||||
|
||||
Users can build PaddlePaddle natively on Linux and Mac OS X. But to unify the building environment and to make it easy for debugging, the recommended way is [using Docker](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/howto/dev/build_en.md).
|
||||
|
||||
1. Keep pulling
|
||||
|
||||
An experienced Git user pulls from the official repo often -- daily or even hourly, so they notice conflicts with others work early, and it's easier to resolve smaller conflicts.
|
||||
|
||||
```bash
|
||||
git remote add upstream https://github.com/PaddlePaddle/Paddle
|
||||
git pull upstream develop
|
||||
```
|
||||
|
||||
1. Push and file a pull request
|
||||
|
||||
You can "push" your local work into your forked repo:
|
||||
|
||||
```bash
|
||||
git push origin my-cool-stuff
|
||||
```
|
||||
|
||||
The push allows you to create a pull request, requesting owners of this [official repo](https://github.com/PaddlePaddle/Paddle) to pull your change into the official one.
|
||||
|
||||
To create a pull request, please follow [these steps](https://help.github.com/articles/creating-a-pull-request/).
|
||||
|
||||
If your change is for fixing an issue, please write ["Fixes <issue-URL>"](https://help.github.com/articles/closing-issues-using-keywords/) in the description section of your pull request. Github would close the issue when the owners merge your pull request.
|
||||
|
||||
Please remember to specify some reviewers for your pull request. If you don't know who are the right ones, please follow Github's recommendation.
|
||||
|
||||
|
||||
1. Delete local and remote branches
|
||||
|
||||
To keep your local workspace and your fork clean, you might want to remove merged branches:
|
||||
|
||||
```bash
|
||||
git push origin :my-cool-stuff
|
||||
git checkout develop
|
||||
git pull upstream develop
|
||||
git branch -d my-cool-stuff
|
||||
```
|
||||
|
||||
### Code Review
|
||||
|
||||
- Please feel free to ping your reviewers by sending them the URL of your pull request via IM or email. Please do this after your pull request passes the CI.
|
||||
|
||||
- Please answer reviewers' every comment. If you are to follow the comment, please write "Done"; please give a reason otherwise.
|
||||
|
||||
- If you don't want your reviewers to get overwhelmed by email notifications, you might reply their comments by [in a batch](https://help.github.com/articles/reviewing-proposed-changes-in-a-pull-request/).
|
||||
|
||||
- Reduce the unnecessary commits. Some developers commit often. It is recommended to append a sequence of small changes into one commit by running `git commit --amend` instead of `git commit`.
|
||||
|
||||
|
||||
## Coding Standard
|
||||
|
||||
### Code Style
|
||||
|
||||
Our C/C++ code follows the [Google style guide](http://google.github.io/styleguide/cppguide.html).
|
||||
|
||||
Our Python code follows the [PEP8 style guide](https://www.python.org/dev/peps/pep-0008/).
|
||||
|
||||
Our build process helps to check the code style. In [`build.sh`](https://github.com/PaddlePaddle/Paddle/blob/b84e8226514b8bb4405c3c28e54aa5077193d179/paddle/scripts/docker/build.sh#L42), the entry point of our [builder Docker image](https://github.com/PaddlePaddle/Paddle/blob/b84e8226514b8bb4405c3c28e54aa5077193d179/Dockerfile#L88), the CMake argument `WITH_STYLE_CHECK` is set to `ON` by default. This flag is on
|
||||
|
||||
Please install pre-commit, which automatically reformat the changes to C/C++ and Python code whenever we run `git commit`. To check the whole codebase, we can run the command `pre-commit run -a`, as in the [`check_style.sh` file](https://github.com/PaddlePaddle/Paddle/blob/b84e8226514b8bb4405c3c28e54aa5077193d179/paddle/scripts/travis/check_style.sh#L30), which is invoked by [our Travis CI configuration](https://github.com/PaddlePaddle/Paddle/blob/b84e8226514b8bb4405c3c28e54aa5077193d179/.travis.yml#L43).
|
||||
|
||||
### Unit Tests
|
||||
|
||||
Please remember to add related unit tests.
|
||||
|
||||
- For C/C++ code, please follow [`google-test` Primer](https://github.com/google/googletest/blob/master/googletest/docs/Primer.md).
|
||||
|
||||
- For Python code, please use [Python's standard `unittest` package](http://pythontesting.net/framework/unittest/unittest-introduction/).
|
||||
|
||||
|
||||
### Writing Logs
|
||||
|
||||
We use [glog](https://github.com/google/glog) for logging in our C/C++ code.
|
||||
|
||||
For general information, please use `LOG`. For debug information, please use [`VLOG`](http://htmlpreview.github.io/?https://github.com/google/glog/blob/master/doc/glog.html#verbose). The reason is at [here](https://groups.google.com/a/chromium.org/d/msg/chromium-dev/3NDNd1KzXeY/AZKMMx37fdQJ).
|
||||
|
||||
`VLOG` requires a *verbose level* parameter. For example:
|
||||
|
||||
```c++
|
||||
VLOG(3) << "Operator FC is taking " << num_inputs << "inputs."
|
||||
```
|
||||
|
||||
When we run a PaddlePaddle application or test, we can specify a verbose threshold. For example:
|
||||
|
||||
```bash
|
||||
GLOG_vmodule=buddy_allocator=2 \
|
||||
GLOG_v=10 \
|
||||
python \
|
||||
../python/paddle/v2/framework/tests/test_recurrent_op.py
|
||||
```
|
||||
|
||||
This will enable VLOG messages generated by `buddy_allocator.{h,cc}` and in the verbose range of 0 to 3, so you will see above example VLOG message, which is in level 3. This suggests that we output overall messages in lower verbose levels, so they display with higher probability. When coding C++, please follow the verbose level convention as follows:
|
||||
|
||||
- verbose level 1: [framework](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/framework)
|
||||
- verbose level 3: [operators](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/operators)
|
||||
- verbose level 5: [memory](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/memory), [platform](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/platform)
|
||||
- verbose level 7: [math](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/math)
|
||||
|
||||
@ -0,0 +1,48 @@
|
||||
# Benchmark
|
||||
|
||||
Machine:
|
||||
|
||||
- Server
|
||||
- Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz, 2 Sockets, 20 Cores per socket
|
||||
- Laptop
|
||||
- DELL XPS15-9560-R1745: i7-7700HQ 8G 256GSSD
|
||||
- i5 MacBook Pro (Retina, 13-inch, Early 2015)
|
||||
- Desktop
|
||||
- i7-6700k
|
||||
|
||||
System: CentOS release 6.3 (Final), Docker 1.12.1.
|
||||
|
||||
PaddlePaddle: paddlepaddle/paddle:latest (TODO: will rerun after 0.11.0)
|
||||
|
||||
- MKL-DNN tag v0.10
|
||||
- MKLML 2018.0.20170720
|
||||
- OpenBLAS v0.2.20
|
||||
|
||||
On each machine, we will test and compare the performance of training on single node using MKL-DNN / MKLML / OpenBLAS respectively.
|
||||
|
||||
## Benchmark Model
|
||||
|
||||
### Server
|
||||
Test on batch size 64, 128, 256 on Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz
|
||||
|
||||
Input image size - 3 * 224 * 224, Time: images/second
|
||||
|
||||
- VGG-19
|
||||
|
||||
| BatchSize | 64 | 128 | 256 |
|
||||
|--------------|-------| -----| --------|
|
||||
| OpenBLAS | 7.82 | 8.62 | 10.34 |
|
||||
| MKLML | 11.02 | 12.86 | 15.33 |
|
||||
| MKL-DNN | 27.69 | 28.8 | 29.27 |
|
||||
|
||||
|
||||
chart on batch size 128
|
||||
TBD
|
||||
|
||||
- ResNet
|
||||
- GoogLeNet
|
||||
|
||||
### Laptop
|
||||
TBD
|
||||
### Desktop
|
||||
TBD
|
||||
@ -0,0 +1,213 @@
|
||||
#!/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_test = get_config_arg("is_test", bool, False)
|
||||
|
||||
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))
|
||||
|
||||
|
||||
#######################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_test)
|
||||
|
||||
|
||||
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.")
|
||||
|
||||
lbl = data_layer(name="label", size=num_class)
|
||||
loss = cross_entropy(name='loss', input=resnet, label=lbl)
|
||||
inputs(img, lbl)
|
||||
outputs(loss)
|
||||
@ -0,0 +1,49 @@
|
||||
set -e
|
||||
|
||||
function train() {
|
||||
unset OMP_NUM_THREADS MKL_NUM_THREADS
|
||||
export OMP_DYNAMIC="FALSE"
|
||||
export KMP_AFFINITY="granularity=fine,compact,0,0"
|
||||
topology=$1
|
||||
layer_num=$2
|
||||
bs=$3
|
||||
use_mkldnn=$4
|
||||
if [ $4 == "True" ]; then
|
||||
thread=1
|
||||
log="logs/${topology}-${layer_num}-mkldnn-${bs}.log"
|
||||
elif [ $4 == "False" ]; then
|
||||
thread=`nproc`
|
||||
# each trainer_count use only 1 core to avoid conflict
|
||||
export OMP_NUM_THREADS=1
|
||||
export MKL_NUM_THREADS=1
|
||||
log="logs/${topology}-${layer_num}-${thread}mklml-${bs}.log"
|
||||
else
|
||||
echo "Wrong input $3, use True or False."
|
||||
exit 0
|
||||
fi
|
||||
args="batch_size=${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}
|
||||
}
|
||||
|
||||
if [ ! -d "train.list" ]; then
|
||||
echo " " > train.list
|
||||
fi
|
||||
if [ ! -d "logs" ]; then
|
||||
mkdir logs
|
||||
fi
|
||||
|
||||
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
|
||||
done
|
||||
done
|
||||
@ -0,0 +1,103 @@
|
||||
#!/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, 19)
|
||||
|
||||
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=0.001 / batch_size,
|
||||
learning_method=MomentumOptimizer(0.9),
|
||||
regularization=L2Regularization(0.0005 * batch_size))
|
||||
|
||||
img = data_layer(name='image', size=height * width * 3)
|
||||
|
||||
|
||||
def vgg_network(vgg_num=3):
|
||||
tmp = img_conv_group(
|
||||
input=img,
|
||||
num_channels=3,
|
||||
conv_padding=1,
|
||||
conv_num_filter=[64, 64],
|
||||
conv_filter_size=3,
|
||||
conv_act=ReluActivation(),
|
||||
pool_size=2,
|
||||
pool_stride=2,
|
||||
pool_type=MaxPooling())
|
||||
|
||||
tmp = img_conv_group(
|
||||
input=tmp,
|
||||
conv_num_filter=[128, 128],
|
||||
conv_padding=1,
|
||||
conv_filter_size=3,
|
||||
conv_act=ReluActivation(),
|
||||
pool_stride=2,
|
||||
pool_type=MaxPooling(),
|
||||
pool_size=2)
|
||||
|
||||
channels = []
|
||||
for i in range(vgg_num):
|
||||
channels.append(256)
|
||||
tmp = img_conv_group(
|
||||
input=tmp,
|
||||
conv_num_filter=channels,
|
||||
conv_padding=1,
|
||||
conv_filter_size=3,
|
||||
conv_act=ReluActivation(),
|
||||
pool_stride=2,
|
||||
pool_type=MaxPooling(),
|
||||
pool_size=2)
|
||||
channels = []
|
||||
for i in range(vgg_num):
|
||||
channels.append(512)
|
||||
tmp = img_conv_group(
|
||||
input=tmp,
|
||||
conv_num_filter=channels,
|
||||
conv_padding=1,
|
||||
conv_filter_size=3,
|
||||
conv_act=ReluActivation(),
|
||||
pool_stride=2,
|
||||
pool_type=MaxPooling(),
|
||||
pool_size=2)
|
||||
tmp = img_conv_group(
|
||||
input=tmp,
|
||||
conv_num_filter=channels,
|
||||
conv_padding=1,
|
||||
conv_filter_size=3,
|
||||
conv_act=ReluActivation(),
|
||||
pool_stride=2,
|
||||
pool_type=MaxPooling(),
|
||||
pool_size=2)
|
||||
|
||||
tmp = fc_layer(
|
||||
input=tmp,
|
||||
size=4096,
|
||||
act=ReluActivation(),
|
||||
layer_attr=ExtraAttr(drop_rate=0.5))
|
||||
|
||||
tmp = fc_layer(
|
||||
input=tmp,
|
||||
size=4096,
|
||||
act=ReluActivation(),
|
||||
layer_attr=ExtraAttr(drop_rate=0.5))
|
||||
|
||||
return fc_layer(input=tmp, size=num_class, act=SoftmaxActivation())
|
||||
|
||||
|
||||
if layer_num == 16:
|
||||
vgg = vgg_network(3)
|
||||
elif layer_num == 19:
|
||||
vgg = vgg_network(4)
|
||||
else:
|
||||
print("Wrong layer number.")
|
||||
|
||||
lab = data_layer('label', num_class)
|
||||
loss = cross_entropy(input=vgg, label=lab)
|
||||
outputs(loss)
|
||||
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue