Migrate some drafts into content/posts with 'draft' flag

content/posts/2017-01-08-retrospect-foresight.org

@@ -2,7 +2,10 @@
 title: Retrospect on Foresight
 author: Chris Hodapp
 date: January 8, 2018
-tags: technobabble, rambling
+tags:
+- technobabble
+- rambling
+draft: true
 ---
 
 /(Spawned from some idle thoughts around the summer of 2015.)/
@@ -48,5 +51,6 @@ wildly impractical, or a mere facade over what is already established.
   foresight.
 - [[https://www.theatlantic.com/magazine/archive/1945/07/as-we-may-think/303881/][As We May Think (Vannevar Bush)]]
 - "Do you remember a time when..." only goes so far.
+- Buckminster Fuller
 
 # Tools For Thought

content/posts/2017-04-20-modularity.org

@@ -1,7 +1,12 @@
-#+TITLE: Modularity & Abstraction (working title)
+---
-#+AUTHOR: Chris Hodapp
+title: Modularity & Abstraction (working title)
-#+DATE: April 20, 2017
+author: Chris Hodapp
-#+TAGS: technobabble
+date: April 20, 2017
+tags:
+- technobabble
+- rambling
+draft: true
+---
 
 # Why don't I turn this into a paper for arXiv too?  It can still be
 # posted to the blog (just also make it exportable to LaTeX perhaps)

content/posts/2017-12-13-retinanet/index.org

@@ -2,9 +2,14 @@
 title: Explaining RetinaNet
 author: Chris Hodapp
 date: December 13, 2017
-tags: technobabble
+tags:
+- technobabble
+draft: true
 ---
 
+# TODO: The inline equations are still broken (maybe because this is
+# in org format)
+
 # Above uses style from https://github.com/turboMaCk/turboMaCk.github.io/blob/develop/posts/2016-12-21-org-mode-in-hakyll.org
 # and https://turbomack.github.io/posts/2016-12-21-org-mode-in-hakyll.html
 # description: 
@@ -29,7 +34,7 @@ taken from
 
 #+CAPTION: TensorFlow object detection example 2.
 #+ATTR_HTML: :width 100% :height 100%
-[[../images/2017-12-13-retinanet/2017-12-13-objdet.jpg]]
+[[./2017-12-13-objdet.jpg]]
 
 At the time of writing, the most accurate object-detection methods
 were based around R-CNN and its variants, and all used two-stage
@@ -109,12 +114,12 @@ approaches while surpassing the accuracy of existing two-stage ones.
 
 At least, this is what the paper claims.  Their novel loss function is
 called *Focal Loss* (as the title references), and it multiplies the
-normal cross-entropy by a factor, $(1-p_t)^\gamma$, where $p_t$
+normal cross-entropy by a factor, \( (1-p_t)^\gamma \), where \( p_t \)
 approaches 1 as the model predicts a higher and higher probability of
-the correct classification, or 0 for an incorrect one, and $\gamma$ is
+the correct classification, or 0 for an incorrect one, and \( \gamma \) is
-a "focusing" hyperparameter (they used $\gamma=2$).  Intuitively, this
+a "focusing" hyperparameter (they used \( \gamma=2 \)).  Intuitively, this
 scaling makes sense: if a classification is already correct (as in the
-"easy negatives"), $(1-p_t)^\gamma$ tends toward 0, and so the portion
+"easy negatives"), \( (1-p_t)^\gamma \) tends toward 0, and so the portion
 of the loss multiplied by it will likewise tend toward 0.
 
 
@@ -152,7 +157,7 @@ diagram illustrates an image pyramid:
 
 #+CAPTION: Source: https://en.wikipedia.org/wiki/File:Image_pyramid.svg
 #+ATTR_HTML: :width 100% :height 100%
-[[../images/2017-12-13-retinanet/1024px-Image_pyramid.svg.png]]
+[[./1024px-Image_pyramid.svg.png]]
 
 Image pyramids have many uses, but the paper focuses on their use in
 taking something that works only at a certain scale of image - for
@@ -180,7 +185,7 @@ CNN:
 
 #+CAPTION: Source: https://commons.wikimedia.org/wiki/File:Typical_cnn.png
 #+ATTR_HTML: :width 100% :height 100%
-[[../images/2017-12-13-retinanet/Typical_cnn.png]]
+[[./Typical_cnn.png]]
 
 You may notice that this network has a structure that bears some
 resemblance to an image pyramid.  This is because deep CNNs are
@@ -262,13 +267,13 @@ inference.
 
 In particular:
 
-- Say that the feature pyramid has $L$ levels, and that level $l+1$ is
+- Say that the feature pyramid has \( L \) levels, and that level \( l+1 \) is
-  half the resolution (thus double the scale) of level $l$.
+  half the resolution (thus double the scale) of level \( l \).
-- Say that level $l$ is a 256-channel feature map of size $W \times H$
+- Say that level \( l \) is a 256-channel feature map of size \( W \times H \)
-  (i.e. it's a tensor with shape $W \times H \times 256$).  Note that
+  (i.e. it's a tensor with shape \( W \times H \times 256 \)).  Note that
-  $W$ and $H$ will be larger at lower levels, and smaller at higher
+  \( W \) and \( H \) will be larger at lower levels, and smaller at higher
   levels, but in RetinaNet at least, always 256-channel samples.
-- For every point on that feature map (all $WH$ of them), we can
+- For every point on that feature map (all \( WH \) of them), we can
   identify a corresponding point in the input image.  This is the
   center point of a broad region of the input image that influences
   this point in the feature map (i.e. its receptive field).  Note that
@@ -279,8 +284,8 @@ In particular:
   rectangular regions associated with each point of a feature map.
   The size of the anchor depends on the scale of the feature map, or
   equivalently, what level of the feature map it came from.  All this
-  means is that anchors in level $l+1$ are twice as large as the
+  means is that anchors in level \( l+1 \) are twice as large as the
-  anchors of level $l$.
+  anchors of level \( l \).
 
 The view that this should paint is that a dense collection of anchors
 covers the entire input image at different sizes - still in a very
@@ -298,7 +303,7 @@ should change the fundamentals.
   elsewhere.
 - It's not a single anchor per 3x3 window, but 9 anchors - one for
   each of three aspect ratios (1:2, 1:1, and 2:1), and each of three
-  scale factors ($1, 2^{1/3}, and 2^{2/3}$) on top of its base scale.
+  scale factors (\( 1, 2^{1/3}, and 2^{2/3} \)) on top of its base scale.
   This is just to handle objects of less-square shapes and to cover
   the gap in scale in between levels of the feature pyramid.  Note
   that the scale factors are evenly-spaced exponentially, such that an
@@ -316,7 +321,7 @@ Every anchor associates an image region with a 3x3 window (i.e. a
 3x3x256 section - it's still 256-channel).  The classification subnet
 is responsible for learning: do the features in this 3x3 window,
 produced from some input, image indicate that an object is inside this
-anchor?  Or, more accurately: For each of $K$ object classes, what's
+anchor?  Or, more accurately: For each of \( K \) object classes, what's
 the probability of each object (or just of it being background)?
 
 ** Box Regression Subnet