Change Step 1 title

Author: EdjeElectronics

README.md

@@ -36,14 +36,13 @@ The purpose of this tutorial is to explain how to train your own convolutional n
 
 There are several good tutorials available for how to use TensorFlow’s Object Detection API to train a classifier for a single object. However, these usually assume you are using a Linux operating system. If you’re like me, you might be a little hesitant to install Linux on your high-powered gaming PC that has the sweet graphics card you’re using to train a classifier. The Object Detection API seems to have been developed on a Linux-based OS. To set up TensorFlow to train a model on Windows, there are several workarounds that need to be used in place of commands that would work fine on Linux. Also, this tutorial provides instructions for training a classifier that can detect multiple objects, not just one.
 
-The tutorial is written for Windows 10, and it will also work for Windows 7 and 8. The general procedure can also be used for Linux operating systems, but file paths and package installation commands will need to change accordingly. 
-
-TensorFlow-GPU allows your PC to use the video card to provide extra processing power while training, so it will be used for this tutorial. In my experience, using TensorFlow-GPU instead of regular TensorFlow reduces training time by a factor of about 8 (3 hours to train instead of 24 hours). Regular TensorFlow can also be used for this tutorial, but it will take longer. If you use regular TensorFlow, you do not need to install CUDA and cuDNN in Step 1. I used TensorFlow-GPU v1.5 while writing the initial version of this tutorial, but it will likely work for future versions of TensorFlow.
+The tutorial is written for Windows 10, and it will also work for Windows 7 and 8. The general procedure can also be used for Linux operating systems, but file paths and package installation commands will need to change accordingly. I used TensorFlow-GPU v1.5 while writing the initial version of this tutorial, but it will likely work for future versions of TensorFlow.
 
+TensorFlow-GPU allows your PC to use the video card to provide extra processing power while training, so it will be used for this tutorial. In my experience, using TensorFlow-GPU instead of regular TensorFlow reduces training time by a factor of about 8 (3 hours to train instead of 24 hours). The CPU-only version of TensorFlow can also be used for this tutorial, but it will take longer. If you use CPU-only TensorFlow, you do not need to install CUDA and cuDNN in Step 1. 
 
 ## Steps
-### 1. Install TensorFlow-GPU, CUDA, and cuDNN
-Follow [this YouTube video by Mark Jay](https://www.youtube.com/watch?v=RplXYjxgZbw), which shows the process for installing CUDA, cuDNN, and TensorFlow-GPU. The video is made for TensorFlow-GPU v1.4, but the “pip install --upgrade tensorflow-gpu” command will automatically download the latest version of TensorFlow (v1.13.1 as of 4/2/19). Download and install the CUDA and cuDNN versions for the latest TensorFlow version, rather than CUDA v8.0 and cuDNN v6.0 as instructed in the video. The [TensorFlow website](https://www.tensorflow.org/install/gpu) indicates which versions of CUDA and cuDNN are needed for the latest version of TensorFlow. 
+### 1. Install Anaconda, CUDA, and cuDNN
+Follow [this YouTube video by Mark Jay](https://www.youtube.com/watch?v=RplXYjxgZbw), which shows the process for installing Anaconda, CUDA, and cuDNN. You do not need to actually install TensorFlow as shown in the video, as we will do that later in Step 2. The video is made for TensorFlow-GPU v1.4, so download and install the CUDA and cuDNN versions for the latest TensorFlow version, rather than CUDA v8.0 and cuDNN v6.0 as instructed in the video. The [TensorFlow website](https://www.tensorflow.org/install/gpu) indicates which versions of CUDA and cuDNN are needed for the latest version of TensorFlow. 
 
 If you are using an older version of TensorFlow, make sure you use the CUDA and cuDNN are compatible with the TensorFlow version you are using. [Here](https://www.tensorflow.org/install/source#tested_build_configurations) is a table showing which version of TensorFlow requires which versions of CUDA and cuDNN.