Updated! My 99.68% solution to Udacity Nanodegree project P2 (Traffic Sign Classification)
There is no change in the previous network structure. However there are some minor changes that leads to the improvement:
- Fix one bug in the code and add L2 regularisation. (This was left out in my previous code)
- Change last dropout to 0.9 and change data augmentation parameters.
Here is a preliminary draft of my report:
And some interesting observations from my report:
- Loss curve
2. Expected probability per class on test set
3. The 40 (0.32%) wrong predictions on the test set
4. Results on internet images
5. Results of network’s data preprocessing layer
Now that I have completed P2, the next project will be P3, Driver Behavioural Cloning. Do stay tuned!