frozenleaves/PyTorchDocs
1
0
Fork 0
mirror of https://github.com/fendouai/PyTorchDocs.git synced 2025-10-20 13:23:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

fgdfg

Browse Source 
dfgf
This commit is contained in:
wyy4github
2019-07-25 17:12:57 +08:00
parent 578306a847
commit a31e0de575
3 changed files with 34 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
.idea/workspace.xml generated
View File

@ -17,12 +17,24 @@
</component>
<component name="FileEditorManager">
<leaf SIDE_TABS_SIZE_LIMIT_KEY="300">
<file pinned="false" current-in-tab="true">
<file pinned="false" current-in-tab="false">
<entry file="file://$PROJECT_DIR$/fourSection/ONNX.md">
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
<state split_layout="SPLIT">
<first_editor relative-caret-position="627">
<caret line="294" selection-start-line="291" selection-end-line="294" />
<first_editor relative-caret-position="-750">
<caret line="158" selection-start-line="158" selection-end-line="158" />
</first_editor>
<second_editor />
</state>
</provider>
</entry>
</file>
<file pinned="false" current-in-tab="true">
<entry file="file://$PROJECT_DIR$/fourSection/AdversarialExampleGene.md">
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
<state split_layout="SPLIT">
<first_editor relative-caret-position="567">
<caret line="21" selection-start-line="21" selection-end-line="21" />
</first_editor>
<second_editor />
</state>
@ -65,9 +77,9 @@
<option value="$PROJECT_DIR$/SecondSection/Tensor.md" />
<option value="$PROJECT_DIR$/tensorTest.py" />
<option value="$PROJECT_DIR$/SecondSection/Autograd.md" />
<option value="$PROJECT_DIR$/fourSection/AdversarialExampleGene.md" />
<option value="$PROJECT_DIR$/Content.md" />
<option value="$PROJECT_DIR$/fourSection/ONNX.md" />
<option value="$PROJECT_DIR$/fourSection/AdversarialExampleGene.md" />
</list>
</option>
</component>
@ -191,7 +203,7 @@
<frame x="-7" y="-7" width="1455" height="935" extended-state="6" />
<editor active="true" />
<layout>
<window_info active="true" content_ui="combo" id="Project" order="0" visible="true" weight="0.10641297" />
<window_info active="true" content_ui="combo" id="Project" order="0" visible="true" weight="0.19661734" />
<window_info id="Structure" order="1" side_tool="true" weight="0.25" />
<window_info id="Favorites" order="2" side_tool="true" />
<window_info anchor="bottom" id="Message" order="0" />
@ -322,16 +334,6 @@
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/fourSection/AdversarialExampleGene.md">
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
<state split_layout="SPLIT">
<first_editor relative-caret-position="573">
<caret line="281" lean-forward="true" selection-start-line="281" selection-end-line="281" />
</first_editor>
<second_editor />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/Content.md">
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
<state split_layout="SPLIT">
@ -345,8 +347,18 @@
<entry file="file://$PROJECT_DIR$/fourSection/ONNX.md">
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
<state split_layout="SPLIT">
<first_editor relative-caret-position="627">
<caret line="294" selection-start-line="291" selection-end-line="294" />
<first_editor relative-caret-position="-750">
<caret line="158" selection-start-line="158" selection-end-line="158" />
</first_editor>
<second_editor />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/fourSection/AdversarialExampleGene.md">
<provider selected="true" editor-type-id="split-provider[text-editor;markdown-preview-editor]">
<state split_layout="SPLIT">
<first_editor relative-caret-position="567">
<caret line="21" selection-start-line="21" selection-end-line="21" />
</first_editor>
<second_editor />
</state>

3
fourSection/AdversarialExampleGene.md
View File

@ -19,6 +19,7 @@ FGSM 攻击是一种白盒攻击，其目标是错误分类。有了这些背景
换句话说，攻击是利用损失函数的梯度，然后调整输入数据以最大化损失。
在进入代码之前，先讲一下著名的 FGSM 熊猫示例并提取一些符号。
![](image/15.png)
从图中可以看出，![](notation/x.gif)是正确分类为“熊猫”的原始输入图像，![](notation/y.gif)是![](notation/x.gif)的基本事实标签，
@ -243,6 +244,7 @@ plt.xlabel("Epsilon")
plt.ylabel("Accuracy")
plt.show()
```
![](image/16.png)
#### 4.2 样本对抗性示例
@ -268,6 +270,7 @@ for i in range(len(epsilons)):
plt.tight_layout()
plt.show()
```
![](image/17.png)
### 5.展望

2
fourSection/ONNX.md
View File

@ -156,7 +156,9 @@ with open('predict_net.pb', "wb") as fopen:
的`init_net`和`predict_net`，并在正常的 Caffe2 后端和移动设备中运行它们，并验证两次运行中生成的输出高分辨率猫咪图像是否相同。
在本教程中，我们将使用广泛使用的著名猫咪图像，如下所示：
![](image/19.jpg)
```buildoutcfg
# 一些必备的导入包
from caffe2.proto import caffe2_pb2