CGIAR_Wheat_Growth_Stage_Challenge

Brief Description

The objective of this challenge is to develop a machine learning model that estimate the growth stage of a wheat crop based on an image sent in by the farmer
For more information about this challenge, have a look on Zindi.

How to run the code

Steps

Make sure to follow the repo structure

1. Run 'resnet152Fastai/resnet152_classif_FastAI.ipynb' to get 'resnet152_classif_FastAI.csv'

2. Run 'resnext50/resnext50.ipynb' to get 'resnext50_regression_pytorch.csv'

3. Run 'vgg16_bn/vgg16_bn_regression_FastAI.ipynb' to get 'vgg16_bn_regression_FastAI.csv'

4. Run 'densenet169/densenet169_Pytorch_Classif.ipynb ' to get'densenet169_Pytorch_Classif.csv'

5. Run 'densnet201_fasati_reg/densenet201_FASTAI__regression.ipynb' to get 'ZION_notebook_densenet201_BS40_size200_350_max_ligh_0.9_max_zoom_1.5_magnitude_0.5.csv'

6. in renext101 you will find 5 notebooks So RUN

      -1- 'resnext101_Pytorch_regression_seed_1.ipynb' 
      -2- 'resnext101_Pytorch_regression_seed_1919.ipynb' 
      -3- 'resnext101_Pytorch_regression_seed_20212020.ipynb' 
      -4- 'resnext101_Pytorch_regression_seed_69.ipynb'
      -5- 'blend_seeds.ipynb' --> and you will get 'final_seed_1_69_1919_20212020.csv'

7. Run 'densenet201/densenet201_classif_FastaAI.ipynb' to get 'densenet201_classif_FastaAI.csv'

8. Run 'Blend/FINAL_BLEND.ipynb' to get 'Final_Blend.csv'

Output

'Final_Blend.csv'

Expectations

To make sure that everything is working smoothly, here is what to expect from above (steps):

Please assert that you run our code with the same GPU performance , you will know our GPU performance by the cell

!nvidia-smi

On the Leaderboard

Look for the team named : SidiSahbi2.0
Rank : 5/204

Authors

Name	Zindi ID	Github ID
Ahmed Attia	@ahmedattia	@ahmedattia
Nacir Bouazizi	@patata	@NacirB
Azer KSOURI	@ASSAZZIN	@Az-Ks

ASSAZZIN-01/CGIAR_Wheat_Growth_Stage_Challenge