llebronc/m5-mcv

Master in Computer Vision - M5 Visual recognition

m5-mcv's Issues

some questions about the preprocess of data for the TT100K database

I would like to ask some questions：
Have you done the same preprocessing as original author to preprocess the data for the TT100K database？Such as perspective transformation, as if not mentioned in your experiment.

Feedback week 2

Overleaf:

• Very good

Google slides:

• Seam unfinished

Github readme:

• Perfect. However it is no necessary to be so long (It takes too much time to do it)

It seams that you woprked hard to get the best mark

Congratulations

Feedback Week 6

Hi,

the slides seem unfinished. The paper complete. Congratulations for the number of methods and experiments you ran in segmentation.

It seems you go for the maximum mark.

assert arguments.config_path is not None, 'Please provide a configuration'\

python2.7 train.py
Using TensorFlow backend.
Traceback (most recent call last):
File "train.py", line 136, in
main()
File "train.py", line 105, in main
assert arguments.config_path is not None, 'Please provide a configuration'
AssertionError: Please provide a configurationpath using -c config/pathname in the command line

Thank you for your help!

Feedback week 4

I've been looking at your deliverable for weeks 3/4 and I think you have done a very good job. I particularly like the way you are presenting things in the READMe.md file. It is neat and clear.

The Overleaf article is well written. However, I miss some implementation details on the paper, so that results can be contextualized and reproduced: e.g. do you train from scratch or fine-tune the network?, which optimizer you use, how many epochs, base_lr? etc. Actually you have all this information on the README file so it's just a matter of summarizing it on the article.

In Tables 3 and 4 of the article I expect to see the final precision/recall and f-score results on the test sets. The avg. recall and avg. IoU metrics of YOLO implementation are a kind of auxiliary metrics in order to see if the model is learning correctly while training, but not really meaningful to compare the different methods. Same thing can be said for slide 11 on your presentation. Also on that slide, I think there is typo on the second row, should it be "Udacity YOLO" instead of "TT100K YOLO"? Please, add the SSD results on the presentation slides.

You should consider adding some images with qualitative results both in the paper and in the slides, I think they may help you to explain the obtained results.

I think you have done a very good work for these two weeks' assignment. Although I cannot see a solution to task (e), I acknowledge the extra work you have done for the SSD model integration, like trying to implement the f-score as a Keras metric and fixing the prediction functionality for detection models. Thus I guess your mark will be close to the maximum.