This is necessary to avoid exploding gradients.
We set the value of 10 through experimentation but it can be adjusted.
blog.algorithmia.com/deep-dive-into-object-detection-with-open-images-using-tensorflow
This is necessary to avoid exploding gradients.
We set the value of 10 through experimentation but it can be adjusted.
blog.algorithmia.com/deep-dive-into-object-detection-with-open-images-using-tensorflow