features.rst
ReST Example
###############
:date: 2020-02-21 16:36:15
:publications_src: content/pages/zotero_single.bib
:toc_run: true
:status: hidden
Links
-----
`ReST documentation <https://docutils.sourceforge.io/rst.html#user-documentation>`__
Table (Playing with Kaggle; uses ReST includes)
-----------------------------------------------
--- snip ---
.. include:: ../includes/ffe/table.rst
--- snap ---
(1) augmented: one additional variant per image rotated randomly in [-5,5] degree.
(2) bn: batch-norm
Mathematics
-----------
*Inline Math:* :math:`f_{i}(x) = \int_{\tau(\pi)}^\infty e(x,y)dy`
*Display Math:*
.. math::
\begin{bmatrix}
a_{11} & a_{12} & \dots \\
\vdots & \ddots & \\
a_{n1} & & a_{nn}
\end{bmatrix}
*Inline Math:* :math:`(\Omega,\mathcal{F},P) \coloneqq (\Omega^+\times\Omega^-,\mathcal{F^+}\otimes\mathcal{F^-},P^+\times P^-)`
*Display Math:*
The Wiener process in :math:`(\Omega,\mathcal{F},P)` is defined by
.. math::
\omega(t) \coloneqq
\left\{
\begin{array}{cc}
(\omega^+(t),0) & t\geq 0 \\
(0,\omega^-(t)) & t<0
\end{array}
\right.
More math ...
.. math::
\tag{3.1a}
\begin{aligned}
dy_t &= \sum_{i=1}^n \frac{x_t^i}{\|x_t\|^2} \left( \sum_{j=1}^n
u_{ij} x_t^i\,dt + \sum_{k=1}^m \sum_{j=1}^n v_{ij}^k
x_t^j\circ dW_t^k\right) + \cdots\\
\cdots &+ \frac{1}{2} \sum_{i,j}^n \left( \frac{\delta_{ij}}{\|x_t\|^2} -
\frac{2x_t^i x_t^j}{\|x_t\|^4} \right)\; \sum_k^m \sum_{l,p}^n
v_{il}^k v_{jp}^k\, x_t^l x_t^p\;dt
\end{aligned}
With :math:`z_t \coloneqq \frac{x_t}{\|x_t\|}` we get the following differential equation on the unit sphere:
.. math::
\tag{3.1b}
\begin{aligned}
y_t &= y_0 + \int_0^t z_t^TUz_t- \|z_t\|^{-2}
z_t^T\hat{V}\hat{V}^T z_t + \frac{1}{2}\text{ trace
}(\hat{V}\hat{V}^T)\,dt +\cdots\\
\cdots &+ \sum_{k=1}^m \int_0^t z_t^TV^kz_t\circ dW_t^k
\end{aligned}
TeX file inclusion
^^^^^^^^^^^^^^^^^^
I was only able to include TeX as a ReST file containing the formulas as valid :code:`math` directive.
--- snip ---
.. include:: ../includes/ffe/formula_0.rst
--- snap ---
Single line:
--- snip ---
Single line (it seems, no real inlining is possible for ReST): start include ->
.. include:: ../includes/ffe/formula_1.rst
<- stop include
--- snap ---
Footnotes
---------
Autonumbered footnotes are
possible, like using [#]_ and [#]_.
Citations
---------
- Cited text 1: [@@touchetteBasicIntroductionLarge2012]
- Cited text 2 [#]_ : [@dematteisRogueWavesLarge2018]
SVG Image
---------
The conversion of the following figure directive will use an <object> tag around the result. This might be blocked by noScript et al.
|
.. figure:: {static}/images/neuron.svg
:align: center
:width: 100%
:figwidth: 50%
:figclass: align-center
Caption (Neuron image - 50%)
Code
----
Verbatim file inclusion
^^^^^^^^^^^^^^^^^^^^^^^
.. include:: ../includes/ffe/features.py
:code:
Normal code block
^^^^^^^^^^^^^^^^^
.. code-block:: none
from torch.utils.data import TensorDataset
from torch import Tensor, LongTensor, FloatTensor
def loadData(path) -> Tuple[np.ndarray, np.ndarray]:
'''
Load data from kaggle mnist set.
path -- input csv
Return scaled images [0,1] and labels (if available)
as numpy arrays (dtype: float32, int64)
'''
# Read
df = pd.read_csv(str(path)) # 40.000 entries
# tdata = pd.read_csv(data_raw_dir + sep + 'train.csv') # 28.000 entries
has_labels = True if 'label' in df.columns else False
Some :code:`inline code`.
.. [#] First footnote
.. [#] Second footnote
.. [#] Interesting in terms of content, by the way
table.rst
================ ====== == ====== ======== ============== =============== ============
Model Epochs bs lr Momentum Result (local) Result (Kaggle) Remarks
================ ====== == ====== ======== ============== =============== ============
SimpleNet 50 20 0.007 0.9 ~97
ConvNet 50 25 0.008 0.9 99.257
" 50 17 0.008 0.9 99.1964 augmented
" 50 17 0.008 0.9 99.3143 99.342 augmented bn
Binary Ensemble 25 17 0.007 0.9 >99
" 22 17 0.0085 0.9 99.23928 99.328 augmented
" 22 17 0.0085 0.9 99.34643 99.357 augmented bn
================ ====== == ====== ======== ============== =============== ============