Shreeyak
commented
6 years ago The last line of "Discussion" is often lost. You could rewrite it something like this:
Discussion is the only section of the report where you may include your opinion. However, make sure your opinion is based on facts.
- Outline your results. If your results are poor, make mention of what may be the underlying issues. If the results are good, why do you think this is the case?
- Reflect on which is more important, inference time or accuracy, in regards to your robotic inference project.
Tips:
Again, avoid writing in the first person (i.e. Do not use words like I or me). If you really find yourself struggling to avoid the word I or me; sometimes, this can be avoid with the use of the word one. As an example: instead of, "I think the accuracy on my dataset is low because the images are too small to show the necessary detail" try, "one may believe the accuracy on the dataset is low because the images are too small to show the necessary detail". They say the same thing, but the second avoids the first person. The above format makes it much easier to reviewers as well.
I've completed a few inference project reviews. I feel there is a lot of ambiguity in the rubric and it could use some refactoring. I would suggest the following: in the content mention that the provided dataset is for students to test out DIGITS and make sure its working properly. Mention that a screenshot of the results should be included. Don't include this in the report. There is no mention of the model on provided dataset anywhere in the report and suddenly an appearance in the results section doesn't make sense.
Where in the report does one talk about the training process and selection of hyperparams? The background section mentions
explaining to the reader how parameters were defined. What params are being referred to here?