A telegram bot that recognize dresses and retrieve similar dresses

python start_fashionizer.py

Create your own conda environment to run FashionizerBOT on your workstation:

In project root:

conda env create -f environment.yml
conda activate VIPM

• Basic implementation of the Bot picked up from dros1986/python_bot.
• start_fashionizer.py does all the works:
• Initialize the Updater that handles the Bot functions and input messages
• Loading of the MaskRCNN Resnet18 and SVM only once when the Bot starts

• MaskRCNN (MatterPort implementation, matterport/Mask_RCNN.)
• Segmentation to identify ROI and classify them as ['clothes', 'no clothes']

Results report

• Resnet18 finetuning
• Resnet18 features + SVM (Kernel = 'rbf', C = 1000, gamma = 1*e-3)
• BoW Features + SVM

Results report

• KDTree from neural features
• KDTree from BOW features

Results report

• Segmentation : MaskRCNN
• Classification : Resnet18 neural features + SVM
• Retrieval : Resnet18 neural features + KdTree

For any questions or doubt do not hesitate to contact us :

• Costantino Carta (c.carta4@campus.unimib.it)
• Hamza Amrani (h.amrani@campus.unimib.it)