PaddleClas/docs/zh_CN/others/feature_visiualization.md

87 lines
3.1 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

# 特征图可视化指南
## 一、概述
特征图是输入图片在卷积网络中的特征表达,对特征图的研究可以有利于我们对于模型的理解与设计,所以基于动态图我们使用本工具来可视化特征图。
## 二、准备工作
首先需要选定研究的模型本文设定ResNet50作为研究模型将模型组网代码[resnet.py](../../../ppcls/arch/backbone/legendary_models/resnet.py)拷贝到[目录](../../../ppcls/utils/feature_maps_visualization/)下,并下载[ResNet50预训练模型](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_pretrained.pdparams),或使用以下命令下载。
```bash
wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_pretrained.pdparams
```
其他模型网络结构代码及预训练模型请自行下载:[模型库](../../../ppcls/arch/backbone/)[预训练模型](../models/models_intro.md)。
## 三、修改模型
找到我们所需要的特征图位置设置self.fm将其fetch出来本文以resnet50中的stem层之后的特征图为例。
在ResNet50的forward函数中指定要可视化的特征图
```python
def forward(self, x):
with paddle.static.amp.fp16_guard():
if self.data_format == "NHWC":
x = paddle.transpose(x, [0, 2, 3, 1])
x.stop_gradient = True
x = self.stem(x)
fm = x
x = self.max_pool(x)
x = self.blocks(x)
x = self.avg_pool(x)
x = self.flatten(x)
x = self.fc(x)
return x, fm
```
然后修改代码[fm_vis.py](../../../ppcls/utils/feature_maps_visualization/fm_vis.py),引入 `ResNet50`,实例化 `net` 对象:
```python
from resnet import ResNet50
net = ResNet50()
```
最后执行函数
```bash
python tools/feature_maps_visualization/fm_vis.py -i the image you want to test \
-c channel_num -p pretrained model \
--show whether to show \
--interpolation interpolation method\
--save_path where to save \
--use_gpu whether to use gpu
```
参数说明:
+ `-i`:待预测的图片文件路径,如 `./test.jpeg`
+ `-c`:特征图维度,如 `5`
+ `-p`:权重文件路径,如 `./ResNet50_pretrained/`
+ `--interpolation`: 图像插值方式, 默认值 1
+ `--save_path`:保存路径,如:`./tools/`
+ `--use_gpu`:是否使用 GPU 预测默认值True
## 四、结果
* 输入图片:
![](../../images/feature_maps/feature_visualization_input.jpg)
* 运行下面的特征图可视化脚本
```
python tools/feature_maps_visualization/fm_vis.py \
-i ./docs/images/feature_maps/feature_visualization_input.jpg \
-c 5 \
-p pretrained/ResNet50_pretrained/ \
--show=True \
--interpolation=1 \
--save_path="./output.png" \
--use_gpu=False
```
* 输出特征图保存为`output.png`,如下所示。
![](../../images/feature_maps/feature_visualization_output.jpg)