Description
Where is the problem?
What can we do better?
Potential for adding a link to the code for numpy_to_tensor.
Changing:
To execute the graph, we first convert the model weights from numpy format to Mojo tensor format, then create the graph, compile it, and run inference. Finally, to check the accuracy, we iterate on test images, preprocess them, obtain the result and calls argmax to find the predicted value between the 10 classes and count how many of them correctly match the ground truth label.
To:
To execute the graph, we first convert the model weights from numpy format to Mojo tensor format, then create the graph, compile it, and run inference. Finally, to check the accuracy, we iterate on test images, preprocess them, obtain the result and calls argmax to find the predicted value between the 10 classes and count how many of them correctly match the ground truth label.
This change could help those following along with the code in the tutorial by explicitly linking where readers can find the code for numpy_to_tensor. Similar to how other sections have links to the documentation for concepts.
Anything else?
I am more than happy to tackle this if we have access to the tutorial.