From 947a0ce154f01e14e69e5cce08e7663d6f734232 Mon Sep 17 00:00:00 2001 From: sushreebarsa <84765720+sushreebarsa@users.noreply.github.com> Date: Thu, 11 Jul 2024 14:34:04 +0530 Subject: [PATCH 1/2] Typos fixing in doc I have updated a few of the typos in TF documentation. Please have a look at this and do the needful. Thank you! --- courses/udacity_deep_learning/2_fullyconnected.ipynb | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/courses/udacity_deep_learning/2_fullyconnected.ipynb b/courses/udacity_deep_learning/2_fullyconnected.ipynb index 6265bb3fe7c..f87b2635763 100644 --- a/courses/udacity_deep_learning/2_fullyconnected.ipynb +++ b/courses/udacity_deep_learning/2_fullyconnected.ipynb @@ -131,15 +131,15 @@ "id": "nCLVqyQ5vPPH" }, "source": [ - "We're first going to train a multinomial logistic regression using simple gradient descent.\n", + "We will first train a multinomial logistic regression using simple gradient descent.\n", "\n", "TensorFlow works like this:\n", - "* First you describe the computation that you want to see performed: what the inputs, the variables, and the operations look like. These get created as nodes over a computation graph. This description is all contained within the block below:\n", + "* First, you describe the computation that you want to see performed: what the inputs, the variables, and the operations look like. These get created as nodes over a computation graph. This description is all contained within the block below:\n", "\n", " with graph.as_default():\n", " ...\n", "\n", - "* Then you can run the operations on this graph as many times as you want by calling `session.run()`, providing it outputs to fetch from the graph that get returned. This runtime operation is all contained in the block below:\n", + "* Then you can run the operations on this graph as many times as you want by calling the `session.run()`, providing it outputs to fetch from the graph that gets returned. This runtime operation is all contained in the block below:\n", "\n", " with tf.Session(graph=graph) as session:\n", " ...\n", From 229e169acbcb94a5cdb4e00f89bfa54448beaa57 Mon Sep 17 00:00:00 2001 From: sushreebarsa <84765720+sushreebarsa@users.noreply.github.com> Date: Thu, 11 Jul 2024 14:48:16 +0530 Subject: [PATCH 2/2] Update 4_convolutions.ipynb --- courses/udacity_deep_learning/4_convolutions.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/courses/udacity_deep_learning/4_convolutions.ipynb b/courses/udacity_deep_learning/4_convolutions.ipynb index 87676a2d2a0..557e5f1e1a0 100644 --- a/courses/udacity_deep_learning/4_convolutions.ipynb +++ b/courses/udacity_deep_learning/4_convolutions.ipynb @@ -14,7 +14,7 @@ "\n", "Previously in `2_fullyconnected.ipynb` and `3_regularization.ipynb`, we trained fully connected networks to classify [notMNIST](http://yaroslavvb.blogspot.com/2011/09/notmnist-dataset.html) characters.\n", "\n", - "The goal of this assignment is make the neural network convolutional." + "The goal of this assignment is to make the neural network convolutional." ] }, { @@ -139,7 +139,7 @@ "id": "5rhgjmROXu2O" }, "source": [ - "Let's build a small network with two convolutional layers, followed by one fully connected layer. Convolutional networks are more expensive computationally, so we'll limit its depth and number of fully connected nodes." + "Let's build a small network with two convolutional layers, followed by one fully connected layer. Convolutional networks are more expensive computationally, so we'll limit their depth and number of fully connected nodes." ] }, {