The notebooks documenting the data collection, data processing and models are in the notebook
folder.
- Data Collection (Naomi)
- Data Exploration and Processing (Yi Xin)
- Data Exploration (Yi Xin)
- Data Preprocessing
- Background Removal (Naomi)
- Data selection (all)
- Baseline CNN and Improvements (Naomi)
- Baseline model
- Improvements to baseline model
- Residual models
- Exploration of Other Networks (Shubhankar)
- RNN+CNN model
- CNN+Attention models
- Local attention
- Convolution self attention
The data used to train the model can be downloaded here
python: 3.9
scikit-image: 0.19.3
scipy: 1.9.3
opencv-python: 4.6.0.66
torchvision; 0.13.1
torchtext: 0.13.1
imagehash: 4.2.1
matplotlib: 3.6.0
pandas: 1.4.3
rembg
numpy: 1.23.4
matplotlib: 3.6.0
opencv-python: 4.6.0.66
torch: >=1.12.1
torchvision; 0.13.1
tqdm
The project presentation slides are available here