Project of Picnic Hackathon 💯🎉 to create solution ✅ that help classify images of product for great customer support 👦, the slogon was When great customer support meets data
One of our core beliefs is to offer our customers the best support possible, by allowing them, for example, to send in pictures of defect products they wish to be reimbursed for. But processing these pictures is very time-consuming as it is all done manually.
The challenge we propose is the following: As a first step in helping customer support, come up with a way of labeling every picture that comes in according to the product that is in the picture. To keep with the Picnic spirit, we encourage to be as innovative and creative with your solutions as possible.
The requirments can be found in each notebook, when using google colab all things are there, you can find google colab notebooks direclty in this Link
I general you will need:
- Fastai Library
- Data science Things (Pandas, Numpy, ..etc)
- GPU power of course!
- Other basic library like glob, path and so on.
In order to get the result I got, you could simply run the The_Picnic_Vision_Submission.ipynb notebook and follow the instruction, you will need the model file which have the trained weight and the architecture, you can access it via this link.
To see how I've trained the model I got you can run the The_Picnic_Vision_Training.ipynb notebook in this repo and follow the instruction.
