DevTeam.Space Developer Profile, Daniil
DevTeam.Space Developer Profile, Daniil ML and Data Science Developer
Daniil is a data scientist with 5 years of experience in machine learning.
Skills and Qualifications
Languages
- Python
Frameworks
- PyTorch
Libraries/APIs
- Tensorflow
- Keras
Tools
- Docker
- DVC
Platforms
- MLFlow
Featured DevTeam.Space Projects
AI, B2B, Backend, ML, Python, Recommendation Engine, TensorFlow
Eksmo is one of the largest publishing houses in Russia. Our machine learning dev team developed neural networks for classifying books by genres. The final system allowed the customer to create a recommendation engine featuring certain books on the publishing house’s advertisements.
Details
Some of Daniil’s Projects
Dozor
This was a project for a carsharing hiring. The project involved creating a system that allowed it to detect and recognize all the faces in the car as well as to detect whether any persons are smoking. The system was required to work offline which was an added challenge. Daniil created a facial recognition solution that could then be embedded into the car’s computer device. He also implemented a cigarette detection solution and a microhiring for preparing face vectors to allow for comparison on a device.
This was a project for a carsharing hiring. The project involved creating a system that allowed it to detect and recognize all the faces in the car as well as to detect whether any persons are smoking. The system was required to work offline which was an added challenge. Daniil created a facial...
Read moreRecognition of goods on the shelves
A solution was needed for merchandisers who compare the real arrangement of goods (realograms) with a plan (planogram). OCR and one-shot learning were used to search the product database using triplet loss network training. The generation of images in Blender was required, as was the development of tools marking real goods. Daniil experimented with various detection and classification approaches, taught OCR models, developed image generation using Blender, and ported and optimized models for Android devices.
A solution was needed for merchandisers who compare the real arrangement of goods (realograms) with a plan (planogram). OCR and one-shot learning were used to search the product database using triplet loss network training. The generation of images in Blender was required, as was the development of...
Read moreHitfactor
A project that was required to find athletic starting signals or shots on a soundtrack. Daniil helped develop an architecture using convolutional and recurrent neural networks. He was also required to allow the system to be able to separate shots coming from other directions, which are not important.
A project that was required to find athletic starting signals or shots on a soundtrack. Daniil helped develop an architecture using convolutional and recurrent neural networks. He was also required to allow the system to be able to separate shots coming from other directions, which are not...
Read more