!2260 Move googlenet to ModelZoo, fix warning and change googlenet's directory
Merge pull request !2260 from liyanliu96/liyanpull/2260/MERGE
mindspore-ci-bot
5 years ago
committed by
Gitee
commit
7f891f62e5
@ -1,106 +0,0 @@
|
||||
# Googlenet Example
|
||||
|
||||
## Description
|
||||
|
||||
This example is for Googlenet model training and evaluation.
|
||||
|
||||
## Requirements
|
||||
|
||||
- Install [MindSpore](https://www.mindspore.cn/install/en).
|
||||
|
||||
- Download the CIFAR-10 binary version dataset.
|
||||
|
||||
> Unzip the CIFAR-10 dataset to any path you want and the folder structure should be as follows:
|
||||
> ```
|
||||
> .
|
||||
> ├── cifar-10-batches-bin # train dataset
|
||||
> └── cifar-10-verify-bin # infer dataset
|
||||
> ```
|
||||
|
||||
## Running the Example
|
||||
|
||||
### Training
|
||||
|
||||
```
|
||||
python train.py --data_path=your_data_path --device_id=6 > out.train.log 2>&1 &
|
||||
```
|
||||
The python command above will run in the background, you can view the results through the file `out.train.log`.
|
||||
|
||||
After training, you'll get some checkpoint files under the script folder by default.
|
||||
|
||||
You will get the loss value as following:
|
||||
```
|
||||
# grep "loss is " out.train.log
|
||||
epoch: 1 step: 390, loss is 1.4842823
|
||||
epcoh: 2 step: 390, loss is 1.0897788
|
||||
...
|
||||
```
|
||||
|
||||
### Evaluation
|
||||
|
||||
```
|
||||
python eval.py --data_path=your_data_path --device_id=6 --checkpoint_path=./train_googlenet_cifar10-125-390.ckpt > out.eval.log 2>&1 &
|
||||
```
|
||||
The above python command will run in the background, you can view the results through the file `out.eval.log`.
|
||||
|
||||
You will get the accuracy as following:
|
||||
```
|
||||
# grep "result: " out.eval.log
|
||||
result: {'acc': 0.934}
|
||||
```
|
||||
|
||||
### Distribute Training
|
||||
```
|
||||
sh run_distribute_train.sh rank_table.json your_data_path
|
||||
```
|
||||
The above shell script will run distribute training in the background, you can view the results through the file `train_parallel[X]/log`.
|
||||
|
||||
You will get the loss value as following:
|
||||
```
|
||||
# grep "result: " train_parallel*/log
|
||||
train_parallel0/log:epoch: 1 step: 48, loss is 1.4302931
|
||||
train_parallel0/log:epcoh: 2 step: 48, loss is 1.4023874
|
||||
...
|
||||
train_parallel1/log:epoch: 1 step: 48, loss is 1.3458025
|
||||
train_parallel1/log:epcoh: 2 step: 48, loss is 1.3729336
|
||||
...
|
||||
...
|
||||
```
|
||||
> About rank_table.json, you can refer to the [distributed training tutorial](https://www.mindspore.cn/tutorial/en/master/advanced_use/distributed_training.html).
|
||||
|
||||
## Usage:
|
||||
|
||||
### Training
|
||||
```
|
||||
usage: train.py [--device_target TARGET][--data_path DATA_PATH]
|
||||
[--device_id DEVICE_ID]
|
||||
|
||||
parameters/options:
|
||||
--device_target the training backend type, default is Ascend.
|
||||
--data_path the storage path of dataset
|
||||
--device_id the device which used to train model.
|
||||
|
||||
```
|
||||
|
||||
### Evaluation
|
||||
|
||||
```
|
||||
usage: eval.py [--device_target TARGET][--data_path DATA_PATH]
|
||||
[--device_id DEVICE_ID][--checkpoint_path CKPT_PATH]
|
||||
|
||||
parameters/options:
|
||||
--device_target the evaluation backend type, default is Ascend.
|
||||
--data_path the storage path of datasetd
|
||||
--device_id the device which used to evaluate model.
|
||||
--checkpoint_path the checkpoint file path used to evaluate model.
|
||||
```
|
||||
|
||||
### Distribute Training
|
||||
|
||||
```
|
||||
Usage: sh run_distribute_train.sh [MINDSPORE_HCCL_CONFIG_PATH] [DATA_PATH]
|
||||
|
||||
parameters/options:
|
||||
MINDSPORE_HCCL_CONFIG_PATH HCCL configuration file path.
|
||||
DATA_PATH the storage path of dataset.
|
||||
```
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,36 @@
|
||||
# Copyright 2020 Huawei Technologies Co., Ltd
|
||||
#
|
||||
# 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.
|
||||
# ============================================================================
|
||||
"""
|
||||
##############export checkpoint file into geir and onnx models#################
|
||||
python export.py
|
||||
"""
|
||||
import numpy as np
|
||||
|
||||
import mindspore as ms
|
||||
from mindspore import Tensor
|
||||
from mindspore.train.serialization import load_checkpoint, load_param_into_net, export
|
||||
|
||||
from src.config import cifar_cfg as cfg
|
||||
from src.googlenet import GoogleNet
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
net = GoogleNet(num_classes=cfg.num_classes)
|
||||
param_dict = load_checkpoint(cfg.checkpoint_path)
|
||||
load_param_into_net(net, param_dict)
|
||||
|
||||
input_arr = Tensor(np.random.uniform(0.0, 1.0, size=[1, 3, 224, 224]), ms.float32)
|
||||
export(net, input_arr, file_name=cfg.onnx_filename, file_format="ONNX")
|
||||
export(net, input_arr, file_name=cfg.geir_filename, file_format="GEIR")
|
||||
@ -0,0 +1,23 @@
|
||||
#!/bin/bash
|
||||
# Copyright 2020 Huawei Technologies Co., Ltd
|
||||
#
|
||||
# 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.
|
||||
# ============================================================================
|
||||
|
||||
ulimit -u unlimited
|
||||
|
||||
BASEPATH=$(cd "`dirname $0`" || exit; pwd)
|
||||
export PYTHONPATH=${BASEPATH}:$PYTHONPATH
|
||||
export DEVICE_ID=0
|
||||
|
||||
python ${BASEPATH}/../eval.py > ./eval.log 2>&1 &
|
||||
@ -0,0 +1,142 @@
|
||||
# Copyright 2020 Huawei Technologies Co., Ltd
|
||||
#
|
||||
# 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.
|
||||
# ============================================================================
|
||||
"""GoogleNet"""
|
||||
import mindspore.nn as nn
|
||||
from mindspore.common.initializer import TruncatedNormal
|
||||
from mindspore.ops import operations as P
|
||||
|
||||
|
||||
def weight_variable():
|
||||
"""Weight variable."""
|
||||
return TruncatedNormal(0.02)
|
||||
|
||||
|
||||
class Conv2dBlock(nn.Cell):
|
||||
"""
|
||||
Basic convolutional block
|
||||
Args:
|
||||
in_channles (int): Input channel.
|
||||
out_channels (int): Output channel.
|
||||
kernel_size (int): Input kernel size. Default: 1
|
||||
stride (int): Stride size for the first convolutional layer. Default: 1.
|
||||
padding (int): Implicit paddings on both sides of the input. Default: 0.
|
||||
pad_mode (str): Padding mode. Optional values are "same", "valid", "pad". Default: "same".
|
||||
Returns:
|
||||
Tensor, output tensor.
|
||||
"""
|
||||
|
||||
def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, pad_mode="same"):
|
||||
super(Conv2dBlock, self).__init__()
|
||||
self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size, stride=stride,
|
||||
padding=padding, pad_mode=pad_mode, weight_init=weight_variable())
|
||||
self.bn = nn.BatchNorm2d(out_channels, eps=0.001)
|
||||
self.relu = nn.ReLU()
|
||||
|
||||
def construct(self, x):
|
||||
x = self.conv(x)
|
||||
x = self.bn(x)
|
||||
x = self.relu(x)
|
||||
return x
|
||||
|
||||
|
||||
class Inception(nn.Cell):
|
||||
"""
|
||||
Inception Block
|
||||
"""
|
||||
|
||||
def __init__(self, in_channels, n1x1, n3x3red, n3x3, n5x5red, n5x5, pool_planes):
|
||||
super(Inception, self).__init__()
|
||||
self.b1 = Conv2dBlock(in_channels, n1x1, kernel_size=1)
|
||||
self.b2 = nn.SequentialCell([Conv2dBlock(in_channels, n3x3red, kernel_size=1),
|
||||
Conv2dBlock(n3x3red, n3x3, kernel_size=3, padding=0)])
|
||||
self.b3 = nn.SequentialCell([Conv2dBlock(in_channels, n5x5red, kernel_size=1),
|
||||
Conv2dBlock(n5x5red, n5x5, kernel_size=3, padding=0)])
|
||||
self.maxpool = P.MaxPoolWithArgmax(ksize=3, strides=1, padding="same")
|
||||
self.b4 = Conv2dBlock(in_channels, pool_planes, kernel_size=1)
|
||||
self.concat = P.Concat(axis=1)
|
||||
|
||||
def construct(self, x):
|
||||
branch1 = self.b1(x)
|
||||
branch2 = self.b2(x)
|
||||
branch3 = self.b3(x)
|
||||
cell, argmax = self.maxpool(x)
|
||||
branch4 = self.b4(cell)
|
||||
_ = argmax
|
||||
return self.concat((branch1, branch2, branch3, branch4))
|
||||
|
||||
|
||||
class GoogleNet(nn.Cell):
|
||||
"""
|
||||
Googlenet architecture
|
||||
"""
|
||||
|
||||
def __init__(self, num_classes):
|
||||
super(GoogleNet, self).__init__()
|
||||
self.conv1 = Conv2dBlock(3, 64, kernel_size=7, stride=2, padding=0)
|
||||
self.maxpool1 = P.MaxPoolWithArgmax(ksize=3, strides=2, padding="same")
|
||||
|
||||
self.conv2 = Conv2dBlock(64, 64, kernel_size=1)
|
||||
self.conv3 = Conv2dBlock(64, 192, kernel_size=3, padding=0)
|
||||
self.maxpool2 = P.MaxPoolWithArgmax(ksize=3, strides=2, padding="same")
|
||||
|
||||
self.block3a = Inception(192, 64, 96, 128, 16, 32, 32)
|
||||
self.block3b = Inception(256, 128, 128, 192, 32, 96, 64)
|
||||
self.maxpool3 = P.MaxPoolWithArgmax(ksize=3, strides=2, padding="same")
|
||||
|
||||
self.block4a = Inception(480, 192, 96, 208, 16, 48, 64)
|
||||
self.block4b = Inception(512, 160, 112, 224, 24, 64, 64)
|
||||
self.block4c = Inception(512, 128, 128, 256, 24, 64, 64)
|
||||
self.block4d = Inception(512, 112, 144, 288, 32, 64, 64)
|
||||
self.block4e = Inception(528, 256, 160, 320, 32, 128, 128)
|
||||
self.maxpool4 = P.MaxPoolWithArgmax(ksize=2, strides=2, padding="same")
|
||||
|
||||
self.block5a = Inception(832, 256, 160, 320, 32, 128, 128)
|
||||
self.block5b = Inception(832, 384, 192, 384, 48, 128, 128)
|
||||
|
||||
self.mean = P.ReduceMean(keep_dims=True)
|
||||
self.dropout = nn.Dropout(keep_prob=0.8)
|
||||
self.flatten = nn.Flatten()
|
||||
self.classifier = nn.Dense(1024, num_classes, weight_init=weight_variable(),
|
||||
bias_init=weight_variable())
|
||||
|
||||
|
||||
def construct(self, x):
|
||||
x = self.conv1(x)
|
||||
x, argmax = self.maxpool1(x)
|
||||
|
||||
x = self.conv2(x)
|
||||
x = self.conv3(x)
|
||||
x, argmax = self.maxpool2(x)
|
||||
|
||||
x = self.block3a(x)
|
||||
x = self.block3b(x)
|
||||
x, argmax = self.maxpool3(x)
|
||||
|
||||
x = self.block4a(x)
|
||||
x = self.block4b(x)
|
||||
x = self.block4c(x)
|
||||
x = self.block4d(x)
|
||||
x = self.block4e(x)
|
||||
x, argmax = self.maxpool4(x)
|
||||
|
||||
x = self.block5a(x)
|
||||
x = self.block5b(x)
|
||||
|
||||
x = self.mean(x, (2, 3))
|
||||
x = self.flatten(x)
|
||||
x = self.classifier(x)
|
||||
|
||||
_ = argmax
|
||||
return x
|
||||
Loading…
Reference in new issue