Aberrations tutorials: Polishing

tutorials/1-getting-started/DTGS126_characterizing_aberrations_cnn.ipynb

@@ -6,7 +6,7 @@
       "source": [
         "# Characterizing Aberrations with a CNN\n",
         "\n",
-        "<a href=\"https://colab.research.google.com/github/softmatterlab/DeepTrack-2.0/blob/develop/examples/tutorials/1-getting-started/DTSG151_characterizing_aberrations_cnn.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+        "<a href=\"https://colab.research.google.com/github/softmatterlab/DeepTrack-2.0/blob/develop/examples/tutorials/1-getting-started/DTSG126_characterizing_aberrations_cnn.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
@@ -15,7 +15,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "# !pip install deeplay deeptrack  # Uncomment if running on Colab/Kaggle."
+        "# !pip install deeplay deeptrack # Uncomment if running on Colab/Kaggle."
       ]
     },
     {
@@ -55,7 +55,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## 2. Define the features\n",
+        "## 2. Defining the Features\n",
         "\n",
         "We define the features needed for this example. \n",
         "\n",
@@ -101,7 +101,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## 3. Combine the features\n",
+        "## 3. Combining the Features\n",
         "\n",
         "To view the particle throught the aberrated microscope, we call `fluorescence_microscope` with both the particle and the aberration. Then we chain the noise and normalization as usual.\n",
         "\n",
@@ -142,7 +142,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## 4. Create the dataset\n",
+        "## 4. Creating the Dataset\n",
         "Using the Pytorch `Dataset` class, we will create a dataset to use for training."
       ]
     },
@@ -197,7 +197,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## 5. Create the model\n",
+        "## 5. Creating the Model\n",
         "\n",
         "We will use a standard convolutional neural network (CNN) with a multilayer perceptron as the dense top for this task. Since this is a regression task, we will use Mean Squared Error (MSE) as the loss metric."
       ]
@@ -248,7 +248,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## 6. Train the model\n",
+        "## 6. Training the Model\n",
         "This can take a few minutes depending on your hardware."
       ]
     },
@@ -342,7 +342,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## 7. Validate the result\n",
+        "## 7. Validating the Results\n",
         "\n",
         "Finally, we validate the result by generating a new dataset and plotting the predicted values of the spherical aberration coefficient against the ground truth."
       ]