lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Morten Hjorth-Jensen
2023-10-30 07:12:05 +01:00
parent f6868e4129
commit 5741161179
12 changed files with 842 additions and 595 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/LectureNotes/data/IMG-2167.JPG
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 338 KiB

doc/LectureNotes/data/luna.JPG
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 22 KiB

doc/pub/week44/html/._week44-bs001.html
+1 -3
View File
@@ -339,9 +339,7 @@ MathJax.Hub.Config({
<div class="panel-body">
<!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
<ul>
<li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v19/material/week5/in5400_2019_week5_convolutional_nerual_networks.pdf" target="_self">Lectures from IN5400 spring 2019</a></li>
<li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v21/lecture-slides/in5400_2021_w5_lecture_convolutions.pdf" target="_self">Lectures from IN5400 spring 2021</a></li>
<li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_self">See also Michael Nielsen's Lectures</a></li>
<li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_self">See Michael Nielsen's Lectures</a></li>
</ul>
</div>
</div>
doc/pub/week44/html/._week44-bs004.html
-7
View File
@@ -308,13 +308,6 @@ efficient to implement and vastly reduce the amount of parameters in
the network.</b>
</p>
<p>Here we provide only a superficial overview, for the more interested, we recommend highly the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_self">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_self">CS231</a>.
</p>
<p>Another good read is the article here <a href="https://arxiv.org/pdf/1603.07285.pdf" target="_self"><tt>https://arxiv.org/pdf/1603.07285.pdf</tt></a>. </p>
<p>
<!-- navigation buttons at the bottom of the page -->
<ul class="pagination">
doc/pub/week44/html/._week44-bs011.html
+1 -2
View File
@@ -312,8 +312,7 @@ MathJax.Hub.Config({
</ul>
<p>For more material on convolutional networks, we strongly recommend
the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_self">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_self">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_self">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
<a href="http://cs231n.github.io/convolutional-networks/" target="_self">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_self">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
</p>
<p>The textbook by Goodfellow et al, see chapter 9 contains an in depth discussion as well.</p>
doc/pub/week44/html/._week44-bs045.html
+3 -3
View File
@@ -1128,7 +1128,7 @@ feed forward neural network.
<span style="color: #008000; font-weight: bold">return</span> g, ker_coef
img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;../data/IMG-2167.JPG&quot;</span>
img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog <span style="color: #666666">=</span> imageio<span style="color: #666666">.</span>imread(img_path, mode<span style="color: #666666">=</span><span style="color: #BA2121">&#39;L&#39;</span>)
plt<span style="color: #666666">.</span>imshow(image_of_cute_dog, cmap<span style="color: #666666">=</span><span style="color: #BA2121">&quot;gray&quot;</span>, vmin<span style="color: #666666">=0</span>, vmax<span style="color: #666666">=255</span>, aspect<span style="color: #666666">=</span><span style="color: #BA2121">&quot;auto&quot;</span>)
@@ -1610,7 +1610,7 @@ layer <span style="color: #666666">=</span> Convolution2DLayer(
)
<span style="color: #408080; font-style: italic"># read in image path, make data correct format</span>
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;../data/IMG-2167.JPG&quot;</span>
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog <span style="color: #666666">=</span> imageio<span style="color: #666666">.</span>imread(img_path)
image_shape <span style="color: #666666">=</span> image_of_cute_dog<span style="color: #666666">.</span>shape
image_of_cute_dog <span style="color: #666666">=</span> image_of_cute_dog<span style="color: #666666">.</span>reshape(<span style="color: #666666">1</span>, image_shape[<span style="color: #666666">0</span>], image_shape[<span style="color: #666666">1</span>], image_shape[<span style="color: #666666">2</span>])
@@ -3474,7 +3474,7 @@ computations.
<span style="color: #008000; font-weight: bold">return</span> conv_image
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;../data/IMG-2167.JPG&quot;</span>
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog <span style="color: #666666">=</span> imageio<span style="color: #666666">.</span>imread(img_path, mode<span style="color: #666666">=</span><span style="color: #BA2121">&quot;L&quot;</span>)
start_time <span style="color: #666666">=</span> time<span style="color: #666666">.</span>time()
filtered_image <span style="color: #666666">=</span> conv2DSep(image_of_cute_dog, kernel<span style="color: #666666">=</span>sobel_kernel, coef<span style="color: #666666">=1</span>)
doc/pub/week44/html/week44-reveal.html
+5 -15
View File
@@ -247,9 +247,7 @@ MathJax.Hub.Config({
<b>And Lecture material on CNNs</b>
<p>
<ul>
<p><li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v19/material/week5/in5400_2019_week5_convolutional_nerual_networks.pdf" target="_blank">Lectures from IN5400 spring 2019</a></li>
<p><li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v21/lecture-slides/in5400_2021_w5_lecture_convolutions.pdf" target="_blank">Lectures from IN5400 spring 2021</a></li>
<p><li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">See also Michael Nielsen's Lectures</a></li>
<p><li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">See Michael Nielsen's Lectures</a></li>
</ul>
</div>
</section>
@@ -290,13 +288,6 @@ into the architecture. These then make the forward function more
efficient to implement and vastly reduce the amount of parameters in
the network.</b>
</p>
<p>Here we provide only a superficial overview, for the more interested, we recommend highly the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_blank">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a>.
</p>
<p>Another good read is the article here <a href="https://arxiv.org/pdf/1603.07285.pdf" target="_blank"><tt>https://arxiv.org/pdf/1603.07285.pdf</tt></a>. </p>
</section>
<section>
@@ -462,8 +453,7 @@ are consistent with the labels in the training set for each image.
<p>
<p>For more material on convolutional networks, we strongly recommend
the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_blank">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
<a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
</p>
<p>The textbook by Goodfellow et al, see chapter 9 contains an in depth discussion as well.</p>
@@ -2473,7 +2463,7 @@ feed forward neural network.
<span style="color: #8B008B; font-weight: bold">return</span> g, ker_coef
img_path = <span style="color: #CD5555">&quot;../data/IMG-2167.JPG&quot;</span>
img_path = <span style="color: #CD5555">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog = imageio.imread(img_path, mode=<span style="color: #CD5555">&#39;L&#39;</span>)
plt.imshow(image_of_cute_dog, cmap=<span style="color: #CD5555">&quot;gray&quot;</span>, vmin=<span style="color: #B452CD">0</span>, vmax=<span style="color: #B452CD">255</span>, aspect=<span style="color: #CD5555">&quot;auto&quot;</span>)
@@ -2955,7 +2945,7 @@ layer = Convolution2DLayer(
)
<span style="color: #228B22"># read in image path, make data correct format</span>
img_path = img_path = <span style="color: #CD5555">&quot;../data/IMG-2167.JPG&quot;</span>
img_path = img_path = <span style="color: #CD5555">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog = imageio.imread(img_path)
image_shape = image_of_cute_dog.shape
image_of_cute_dog = image_of_cute_dog.reshape(<span style="color: #B452CD">1</span>, image_shape[<span style="color: #B452CD">0</span>], image_shape[<span style="color: #B452CD">1</span>], image_shape[<span style="color: #B452CD">2</span>])
@@ -4820,7 +4810,7 @@ computations.
<span style="color: #8B008B; font-weight: bold">return</span> conv_image
img_path = img_path = <span style="color: #CD5555">&quot;../data/IMG-2167.JPG&quot;</span>
img_path = img_path = <span style="color: #CD5555">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog = imageio.imread(img_path, mode=<span style="color: #CD5555">&quot;L&quot;</span>)
start_time = time.time()
filtered_image = conv2DSep(image_of_cute_dog, kernel=sobel_kernel, coef=<span style="color: #B452CD">1</span>)
doc/pub/week44/html/week44-solarized.html
+5 -15
View File
@@ -294,9 +294,7 @@ MathJax.Hub.Config({
<b>And Lecture material on CNNs</b>
<p>
<ul>
<li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v19/material/week5/in5400_2019_week5_convolutional_nerual_networks.pdf" target="_blank">Lectures from IN5400 spring 2019</a></li>
<li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v21/lecture-slides/in5400_2021_w5_lecture_convolutions.pdf" target="_blank">Lectures from IN5400 spring 2021</a></li>
<li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">See also Michael Nielsen's Lectures</a></li>
<li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">See Michael Nielsen's Lectures</a></li>
</ul>
</div>
@@ -336,13 +334,6 @@ efficient to implement and vastly reduce the amount of parameters in
the network.</b>
</p>
<p>Here we provide only a superficial overview, for the more interested, we recommend highly the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_blank">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a>.
</p>
<p>Another good read is the article here <a href="https://arxiv.org/pdf/1603.07285.pdf" target="_blank"><tt>https://arxiv.org/pdf/1603.07285.pdf</tt></a>. </p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="neural-networks-vs-cnns">Neural Networks vs CNNs </h2>
@@ -497,8 +488,7 @@ are consistent with the labels in the training set for each image.
</ul>
<p>For more material on convolutional networks, we strongly recommend
the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_blank">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
<a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
</p>
<p>The textbook by Goodfellow et al, see chapter 9 contains an in depth discussion as well.</p>
@@ -2419,7 +2409,7 @@ feed forward neural network.
<span style="color: #8B008B; font-weight: bold">return</span> g, ker_coef
img_path = <span style="color: #CD5555">&quot;../data/IMG-2167.JPG&quot;</span>
img_path = <span style="color: #CD5555">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog = imageio.imread(img_path, mode=<span style="color: #CD5555">&#39;L&#39;</span>)
plt.imshow(image_of_cute_dog, cmap=<span style="color: #CD5555">&quot;gray&quot;</span>, vmin=<span style="color: #B452CD">0</span>, vmax=<span style="color: #B452CD">255</span>, aspect=<span style="color: #CD5555">&quot;auto&quot;</span>)
@@ -2901,7 +2891,7 @@ layer = Convolution2DLayer(
)
<span style="color: #228B22"># read in image path, make data correct format</span>
img_path = img_path = <span style="color: #CD5555">&quot;../data/IMG-2167.JPG&quot;</span>
img_path = img_path = <span style="color: #CD5555">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog = imageio.imread(img_path)
image_shape = image_of_cute_dog.shape
image_of_cute_dog = image_of_cute_dog.reshape(<span style="color: #B452CD">1</span>, image_shape[<span style="color: #B452CD">0</span>], image_shape[<span style="color: #B452CD">1</span>], image_shape[<span style="color: #B452CD">2</span>])
@@ -4765,7 +4755,7 @@ computations.
<span style="color: #8B008B; font-weight: bold">return</span> conv_image
img_path = img_path = <span style="color: #CD5555">&quot;../data/IMG-2167.JPG&quot;</span>
img_path = img_path = <span style="color: #CD5555">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog = imageio.imread(img_path, mode=<span style="color: #CD5555">&quot;L&quot;</span>)
start_time = time.time()
filtered_image = conv2DSep(image_of_cute_dog, kernel=sobel_kernel, coef=<span style="color: #B452CD">1</span>)
doc/pub/week44/html/week44.html
+5 -15
View File
@@ -371,9 +371,7 @@ MathJax.Hub.Config({
<b>And Lecture material on CNNs</b>
<p>
<ul>
<li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v19/material/week5/in5400_2019_week5_convolutional_nerual_networks.pdf" target="_blank">Lectures from IN5400 spring 2019</a></li>
<li> <a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/v21/lecture-slides/in5400_2021_w5_lecture_convolutions.pdf" target="_blank">Lectures from IN5400 spring 2021</a></li>
<li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">See also Michael Nielsen's Lectures</a></li>
<li> <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">See Michael Nielsen's Lectures</a></li>
</ul>
</div>
@@ -413,13 +411,6 @@ efficient to implement and vastly reduce the amount of parameters in
the network.</b>
</p>
<p>Here we provide only a superficial overview, for the more interested, we recommend highly the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_blank">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a>.
</p>
<p>Another good read is the article here <a href="https://arxiv.org/pdf/1603.07285.pdf" target="_blank"><tt>https://arxiv.org/pdf/1603.07285.pdf</tt></a>. </p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
<h2 id="neural-networks-vs-cnns">Neural Networks vs CNNs </h2>
@@ -574,8 +565,7 @@ are consistent with the labels in the training set for each image.
</ul>
<p>For more material on convolutional networks, we strongly recommend
the course
<a href="https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html" target="_blank">IN5400 &#8211; Machine Learning for Image Analysis</a>
and the slides of <a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
<a href="http://cs231n.github.io/convolutional-networks/" target="_blank">CS231</a> which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). <a href="http://neuralnetworksanddeeplearning.com/chap6.html" target="_blank">Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs</a>.
</p>
<p>The textbook by Goodfellow et al, see chapter 9 contains an in depth discussion as well.</p>
@@ -2496,7 +2486,7 @@ feed forward neural network.
<span style="color: #008000; font-weight: bold">return</span> g, ker_coef
img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;../data/IMG-2167.JPG&quot;</span>
img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog <span style="color: #666666">=</span> imageio<span style="color: #666666">.</span>imread(img_path, mode<span style="color: #666666">=</span><span style="color: #BA2121">&#39;L&#39;</span>)
plt<span style="color: #666666">.</span>imshow(image_of_cute_dog, cmap<span style="color: #666666">=</span><span style="color: #BA2121">&quot;gray&quot;</span>, vmin<span style="color: #666666">=0</span>, vmax<span style="color: #666666">=255</span>, aspect<span style="color: #666666">=</span><span style="color: #BA2121">&quot;auto&quot;</span>)
@@ -2978,7 +2968,7 @@ layer <span style="color: #666666">=</span> Convolution2DLayer(
)
<span style="color: #408080; font-style: italic"># read in image path, make data correct format</span>
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;../data/IMG-2167.JPG&quot;</span>
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog <span style="color: #666666">=</span> imageio<span style="color: #666666">.</span>imread(img_path)
image_shape <span style="color: #666666">=</span> image_of_cute_dog<span style="color: #666666">.</span>shape
image_of_cute_dog <span style="color: #666666">=</span> image_of_cute_dog<span style="color: #666666">.</span>reshape(<span style="color: #666666">1</span>, image_shape[<span style="color: #666666">0</span>], image_shape[<span style="color: #666666">1</span>], image_shape[<span style="color: #666666">2</span>])
@@ -4842,7 +4832,7 @@ computations.
<span style="color: #008000; font-weight: bold">return</span> conv_image
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;../data/IMG-2167.JPG&quot;</span>
img_path <span style="color: #666666">=</span> img_path <span style="color: #666666">=</span> <span style="color: #BA2121">&quot;data/IMG-2167.JPG&quot;</span>
image_of_cute_dog <span style="color: #666666">=</span> imageio<span style="color: #666666">.</span>imread(img_path, mode<span style="color: #666666">=</span><span style="color: #BA2121">&quot;L&quot;</span>)
start_time <span style="color: #666666">=</span> time<span style="color: #666666">.</span>time()
filtered_image <span style="color: #666666">=</span> conv2DSep(image_of_cute_dog, kernel<span style="color: #666666">=</span>sobel_kernel, coef<span style="color: #666666">=1</span>)
doc/pub/week44/ipynb/ipynb-week44-src.tar.gz
BIN
View File
Binary file not shown.
doc/pub/week44/ipynb/week44.ipynb
+817 -520
View File
File diff suppressed because it is too large Load Diff
doc/src/week44/week44.do.txt
+5 -15
View File
@@ -25,9 +25,7 @@ DATE: October 30-November 3
!eblock
!bblock And Lecture material on CNNs
* "Lectures from IN5400 spring 2019":"https://www.uio.no/studier/emner/matnat/ifi/IN5400/v19/material/week5/in5400_2019_week5_convolutional_nerual_networks.pdf"
* "Lectures from IN5400 spring 2021":"https://www.uio.no/studier/emner/matnat/ifi/IN5400/v21/lecture-slides/in5400_2021_w5_lecture_convolutions.pdf"
* "See also Michael Nielsen's Lectures":"http://neuralnetworksanddeeplearning.com/chap6.html"
* "See Michael Nielsen's Lectures":"http://neuralnetworksanddeeplearning.com/chap6.html"
!eblock
@@ -65,13 +63,6 @@ into the architecture. These then make the forward function more
efficient to implement and vastly reduce the amount of parameters in
the network._
Here we provide only a superficial overview, for the more interested, we recommend highly the course
"IN5400 – Machine Learning for Image Analysis":"https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html"
and the slides of "CS231":"http://cs231n.github.io/convolutional-networks/".
Another good read is the article here URL:"https://arxiv.org/pdf/1603.07285.pdf".
!split
@@ -209,8 +200,7 @@ In summary:
For more material on convolutional networks, we strongly recommend
the course
"IN5400 – Machine Learning for Image Analysis":"https://www.uio.no/studier/emner/matnat/ifi/IN5400/index-eng.html"
and the slides of "CS231":"http://cs231n.github.io/convolutional-networks/" which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). "Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs":"http://neuralnetworksanddeeplearning.com/chap6.html".
"CS231":"http://cs231n.github.io/convolutional-networks/" which is taught at Stanford University (consistently ranked as one of the top computer science programs in the world). "Michael Nielsen's book is a must read, in particular chapter 6 which deals with CNNs":"http://neuralnetworksanddeeplearning.com/chap6.html".
The textbook by Goodfellow et al, see chapter 9 contains an in depth discussion as well.
@@ -1713,7 +1703,7 @@ def generate_gauss_mask(sigma, K=1):
return g, ker_coef
img_path = "../data/IMG-2167.JPG"
img_path = "data/IMG-2167.JPG"
image_of_cute_dog = imageio.imread(img_path, mode='L')
plt.imshow(image_of_cute_dog, cmap="gray", vmin=0, vmax=255, aspect="auto")
@@ -2140,7 +2130,7 @@ layer = Convolution2DLayer(
)
# read in image path, make data correct format
img_path = img_path = "../data/IMG-2167.JPG"
img_path = img_path = "data/IMG-2167.JPG"
image_of_cute_dog = imageio.imread(img_path)
image_shape = image_of_cute_dog.shape
image_of_cute_dog = image_of_cute_dog.reshape(1, image_shape[0], image_shape[1], image_shape[2])
@@ -3773,7 +3763,7 @@ def conv2DSep(image, kernel, coef, stride=1, pad="zero"):
return conv_image
img_path = img_path = "../data/IMG-2167.JPG"
img_path = img_path = "data/IMG-2167.JPG"
image_of_cute_dog = imageio.imread(img_path, mode="L")
start_time = time.time()
filtered_image = conv2DSep(image_of_cute_dog, kernel=sobel_kernel, coef=1)