Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pull Request for DL-Simplified 💡
Issue Title : Honey Bee Pollen Detection #346
Email ID : [email protected]
JWOC Participant
) SSOC23Closes: #346
Describe the add-ons or changes you've made 📃
Implemented a CNN, DenseNet and VGG16 for image classification to predict whether the given image of honey bee contains pollen or not.
During the honeybee image pollen detection project, several add-ons were incorporated to enhance the overall performance and usability of the model.
Firstly, data augmentation techniques were applied to increase the dataset's diversity, enabling the model to handle variations in image conditions effectively.
Secondly, transfer learning was leveraged using pre-trained VGG16 and DenseNet architectures to expedite training and improve accuracy. Additionally, a post-processing step was implemented, applying a threshold to the model's output probabilities for confident binary predictions.
Updated the README file with detailed instructions and documentation.
Type of change ☑️
What sort of change have you made:
How Has This Been Tested? ⚙️
To keep a clean code and concentrate on one model at a time, I decided to take the approach of creating separate ipynb files for each models. Aside from the model architecture, all models' code adheres to the same process for all other aspects.
The evaluation metrics I used to assess the models:
Accuracy
Loss
Checklist: ☑️