This is an automated email from the ASF dual-hosted git repository.
skm pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/master by this push:
new 2bc4430 Clarify dependency on OpenCV in CNN Visualization tutorial.
(#13495)
2bc4430 is described below
commit 2bc4430c9c9999640a34df4a606a89b74b12008f
Author: Vishaal Kapoor <[email protected]>
AuthorDate: Fri Nov 30 23:35:42 2018 -0800
Clarify dependency on OpenCV in CNN Visualization tutorial. (#13495)
---
docs/tutorials/vision/cnn_visualization.md | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/docs/tutorials/vision/cnn_visualization.md
b/docs/tutorials/vision/cnn_visualization.md
index 63d2b13..5ded6f1 100644
--- a/docs/tutorials/vision/cnn_visualization.md
+++ b/docs/tutorials/vision/cnn_visualization.md
@@ -1,16 +1,21 @@
# Visualizing Decisions of Convolutional Neural Networks
-Convolutional Neural Networks have made a lot of progress in Computer Vision.
Their accuracy is as good as humans in some tasks. However it remains hard to
explain the predictions of convolutional neural networks, as they lack the
interpretability offered by other models, for example decision trees.
+Convolutional Neural Networks have made a lot of progress in Computer Vision.
Their accuracy is as good as humans in some tasks. However, it remains
difficult to explain the predictions of convolutional neural networks, as they
lack the interpretability offered by other models such as decision trees.
-It is often helpful to be able to explain why a model made the prediction it
made. For example when a model misclassifies an image, it is hard to say why
without visualizing the network's decision.
+It is often helpful to be able to explain why a model made the prediction it
made. For example, when a model misclassifies an image, without visualizing the
network's decision, it is hard to say why the misclassification was made.
<img align="right"
src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/example/cnn_visualization/volcano_barn_spider.png";
alt="Explaining the misclassification of volcano as spider" width=500px/>
-Visualizations also help build confidence about the predictions of a model.
For example, even if a model correctly predicts birds as birds, we would want
to confirm that the model bases its decision on the features of bird and not on
the features of some other object that might occur together with birds in the
dataset (like leaves).
+Visualizations can also build confidence about the predictions of a model. For
example, even if a model correctly predicts birds as birds, we would want to
confirm that the model bases its decision on the features of bird and not on
the features of some other object that might occur together with birds in the
dataset (like leaves).
-In this tutorial, we show how to visualize the predictions made by
convolutional neural networks using [Gradient-weighted Class Activation
Mapping](https://arxiv.org/abs/1610.02391). Unlike many other visualization
methods, Grad-CAM can be used on a wide variety of CNN model families - CNNs
with fully connected layers, CNNs used for structural outputs (e.g.
captioning), CNNs used in tasks with multi-model input (e.g. VQA) or
reinforcement learning without architectural changes or re-training.
+In this tutorial we show how to visualize the predictions made by
convolutional neural networks using [Gradient-weighted Class Activation
Mapping](https://arxiv.org/abs/1610.02391). Unlike many other visualization
methods, Grad-CAM can be used on a wide variety of CNN model families - CNNs
with fully connected layers, CNNs used for structural outputs (e.g.
captioning), CNNs used in tasks with multi-model input (e.g. VQA) or
reinforcement learning without architectural changes or re-training.
-In the rest of this notebook, we will explain how to visualize predictions
made by [VGG-16](https://arxiv.org/abs/1409.1556). We begin by importing the
required dependencies. `gradcam` module contains the implementation of
visualization techniques used in this notebook.
+In the rest of this notebook, we will explain how to visualize predictions
made by [VGG-16](https://arxiv.org/abs/1409.1556). We begin by importing the
required dependencies.
+
+## Prerequesites
+* OpenCV is required by `gradcam` (below) and can be installed with pip using
`pip opencv-python`.
+
+* the `gradcam` module contains the implementation of visualization techniques
used in this notebook. `gradcam` can be installed to a temporary directory by
executing the following code block.
```python
from __future__ import print_function
![https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/example/cnn_visualization/volcano_barn_spider.png"](https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/example/cnn_visualization/volcano_barn_spider.png"){kind=link}