Nitin Rai's Projects
Weed Prescription Map using Arcpy and Python
Implemented Image Classification on RStudio on Maize and Sugarbeet Dataset. Tuned several parameters and number of epochs along with the learning rate to increase the prediction accuracy.
MicaSense RedEdge and Altum image processing tutorials
Jithin Mathew
Implemented KMeans on an orthomsaicked image of Barley Plots.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data.
A comprehensive machine learning repository containing 30+ notebooks on different concepts, algorithms and techniques.
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
A beautiful, simple, clean, and responsive Jekyll theme for academics
This is a cloned repository from JetHacks. I have worked on implementing real-time Watershed Segmentation. You'll find the algorithm (.py) in Examples folder. Let me know if I can make the algorithm more efficient. Also, JetsonTX2's inbuilt camera is not switching on by default. I have tried to change certain command lines in python to switch to the camera but it simply fails. I think the problem might be in gstreamer support and OpenCV version. I'm still working on this issue and will update the repository once the problem is fixed.
Comes under organizing dataset with defined labels for each images in a directory.
This routine can be used to resize any number of images inside a directory. Was useful in implementing CNN on a huge datasets.
Sometimes downloaded dataset are all messed up and scattered. This algorithm helps in classifying dataset according to the classes of your choice.
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors