Получил проект в институте и не успеваю его сдать. Нужен тот кто сможет мне помочь.

Нужно создать ML решение которое может определять:
- wrinkles (binary: has/does_not_have), class 0: does_not_have, class 1: has

- freakles (binary: has/does_not_have), class 0: does_not_have, class 1: has

- glasses (3 values: do_not_wear/wear_normal/wear_sunglasses), class 0:
does_not_wear, class 1: wear_ normal, class 2: wear_sunglasses

- hair_color (9 values: brown/black/gray/blond/red/white/mixed/other/not_visible),
class 0: brown, class 1: black, class 2: gray, class 3: blond, class 4: red, class 5: white,
class 6: mixed, class 7: other, class 8: not_visible

- hair_top (4 values: bald or shaved, has_few_hair, has_thick_hair, not_visible), class 0:
bald or shaved, class 1: has_few_hair, class 2: has_thick_hair, class 3: not_visible

Архив с картинками имеется.


Нужно использовать следующие методы:

- Data Labelling (10 marks; it will be possible to obtain 10 more marks if an
additionally provided dataset is also labeled and used; this additional dataset to
be provided upon request)

- Data Splitting (in training and validation sets) & Data Statistics (eg. label
distributions per attribute and per set) (5 marks)

- Data Pre-processing (data augmentation, normalization/standardization,
over/under-sampling) (5 marks)
o 2 ML Methodologies (a basic one & an additional one): appropriate ML methods
should be used that have coherent implementations and sound pipelines, without
any errors; (if the basic ML method is a DNN, the additional one can be another
DNN) (30 marks)

- Evaluation of the 2 methods using different metrics (5 marks)

Нужно будет записать видео на минут 5-10 где вы (на русском) объясните как работает вся программа.

Полное описание вы найдете в прикрепленном файле.