Fix typos

aleju · Mar 14, 2017 · 90cdd82 · 90cdd82
1 parent 4de2db0
commit 90cdd82
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 1 deletion.
diff --git a/neural-nets/Fast_R-CNN.md b/neural-nets/Fast_R-CNN.md
@@ -6,6 +6,8 @@
 * **Tags**: Neural Network, RCNN, VGG, AlexNet, selective search
 * **Year**: 2015
 
+# Summary
+
 * What
   * The original R-CNN had three major disadvantages:
     1. Two-staged training pipeline: Instead of only training a CNN, one had to train first a CNN and then multiple SVMs.
@@ -79,6 +81,7 @@
     * mAP improves from 66.0% to 66.6% (66.9% without SVD).
     * Per class accuracy results:
       * Fast_R-CNN__pvoc2012.jpg
+      * ![VOC2012 results](images/Fast_R-CNN__pvoc2012.jpg?raw=true "VOC2012 results")
   * Fixing the weights of VGG16's convolutional layers and only fine-tuning the fully connected layers (those are applied to each region proposal), decreases the accuracy to 61.4%.
     * This decrease in accuracy is most significant for the later convolutional layers, but marginal for the first layers.
     * Therefor they only train the convolutional layers starting with `conv3_1` (9 out of 13 layers), which speeds up training.

diff --git a/neural-nets/Faster_R-CNN.md b/neural-nets/Faster_R-CNN.md
@@ -6,6 +6,8 @@
 * **Tags**: Neural Network, RCNN
 * **Year**: 2015
 
+# Summary
+
 * What
   * R-CNN and its successor Fast R-CNN both rely on a "classical" method to find region proposals in images (i.e. "Which regions of the image look like they *might* be objects?").
   * That classical method is selective search.

diff --git a/neural-nets/Instance_Normalization_The_Missing_Ingredient_for_Fast_Stylization.md b/neural-nets/Instance_Normalization_The_Missing_Ingredient_for_Fast_Stylization.md
@@ -24,7 +24,7 @@
       * ![Batch Normalization Equations](images/Instance_Normalization_The_Missing_Ingredient_for_Fast_Stylization__batch_normalization.jpg?raw=true "Batch Normalization Equations")
     * Instance Normalization
       * ![Instance Normalization Equations](images/Instance_Normalization_The_Missing_Ingredient_for_Fast_Stylization__instance_normalization.jpg?raw=true "Instance Normalization Equations")
-  * They apply instance normalization and test time too (identically).
+  * They apply instance normalization at test time too (identically).
 
 * Results
   * Same image quality as iterative approach (at a fraction of the runtime).