From the course: TensorFlow 2.0: Working with Images

Unlock the full course today

Join today to access over 24,400 courses taught by industry experts.

Using TensorBoard

Using TensorBoard

From the course: TensorFlow 2.0: Working with Images

Start my 1-month free trial Buy for my team

Using TensorBoard

“

- [Instructor] TensorBoard provides a visual representation of how model parameters evolve throughout the training cycle. It's often used for training model accuracy over training epochs. TensorFlow can also let you see how weights and biases evolve in each model layer. And just like ModelCheckpoint and Early Stopping, TensorBoard is applied to the training process via the callbacks module. Just so that we have a clean starting point, I'm going to reset our notebook and start again for TensorBoard. I'm going to head over to Runtime. I'm going to select Factory reset runtime. And I'm going to reset that notebook. I'm going to select Reconnect, and then go ahead and run the next couple of cells. And you can see that we've got the same model. But what's different here is that we've got a name for each of the layers. So for our first convolution layer, we've got it as conv 1. Similarly, we've got a conv 2 for our…

Contents