website

Apply-Network1.py

@@ -1,20 +1,20 @@
-from keras.models import load_model
-from orcs.process import SpectralCube
 import os
 import numpy as np
 import matplotlib.pyplot as plt
+import time
 from keras import activations
 from keras.models import Sequential
 from keras.layers import Dense, InputLayer, Flatten, Dropout
 from keras.layers.convolutional import Conv1D
 from keras.layers.convolutional import MaxPooling1D
 from keras.optimizers import Adam
 from keras.callbacks import EarlyStopping, ReduceLROnPlateau
+from keras.models import load_model
+from orcs.process import SpectralCube
 from astropy.io import fits
 from pickle import load
-from tqdm import tqdm_notebook as tqdm
 from scipy import interpolate
-import time
+
 
 #--------------------------------- INPUTS -------------------------------------#
 home_dir = '/path/to/main/directory/containing/data'   # Location weights file

ApplyDataCube.html

@@ -0,0 +1,41 @@
+<p>
+  This example will guide you through the process of applying a pre-trained network (i.e. the weights have been trained),
+  to a SITELLE data cube. This example will use the network trained to predict velocity and broadening values, therefore,
+  we will be applying this to an SN3 cube.
+</p>
+<p>
+  The code will read in a the network and a datacube. We will then step through each pixel in the datacube, extract the
+  spectrum, subtract the background, interpolate the background-subtracted spectrum onto the reference spectrum's x-axis,
+  and finally apply the network to extract the velocity and broadening parameters. Let's start with our imports -- I apologize
+  for all of them!
+</p>
+<pre class="line-numbers">
+  <code class="language-python">
+    import os
+    import numpy as np
+    import matplotlib.pyplot as plt
+    import time
+    from keras.optimizers import Adam
+    from keras.models import load_model
+    from orcs.process import SpectralCube
+    from astropy.io import fits
+    from pickle import load
+    from scipy import interpolate
+  </code>
+</pre>
+
+<p>
+  Now we need to define our directories, cube name, and location of the deep frame. If you have not created a deep frame
+  for the cube, please do so now. Also, be sure to have the reference spectrum in the home directory.
+</p>
+
+<pre>
+  <code class="language-python">
+    home_dir = '/path/to/main/directory/containing/data'   # Location weights file
+    cube_dir = '/path/to/cubes'  # Path to data cube
+    cube_name = 'cube_name'  # don't add .hdf5 extension
+    output_dir = '/path/to/output'  # Path to output directory
+    output_name = 'output_name'  # output file prefix
+    deep_file = '/full/path/to/deep/fits'  # Path to deep image fits file: required for header
+  </code>
+</pre>

css/business-frontpage.css

@@ -0,0 +1,8 @@
+/*!
+ * Start Bootstrap - Business Frontpage (https://startbootstrap.com/template/business-frontpage)
+ * Copyright 2013-2020 Start Bootstrap
+ * Licensed under MIT (https://github.com/StartBootstrap/startbootstrap-business-frontpage/blob/master/LICENSE)
+ */
+body {
+  padding-top: 56px;
+}

css/main.css

@@ -0,0 +1,19 @@
+body {
+  padding-top: 56px;
+}
+
+h2 {
+  padding-top: 20px;
+}
+
+/* pygments highlight */
+.highlight {
+  border: 1px solid #cfcfcf;
+  padding-top: 10px;
+  padding-left: 10px;
+  padding-right: 10px;
+  border-radius: 2px;
+  background: #f7f7f7;
+  line-height: 1.21429em;
+  margin-bottom: 10px;
+}