AlexOlsen/DeepWeeds
A Multiclass Weed Species Image Dataset for Deep Learning
Contains 17,509 in-situ field images of eight Australian weed species with pre-trained ResNet50 and InceptionV3 models achieving 95.7% average accuracy. Integrates with TensorFlow Datasets for streamlined access, and includes C++ TensorRT inference code for deployment on NVIDIA Jetson TX2 platforms. Training pipeline uses five-fold cross-validation with ImageNet pre-trained weights via Keras.
245 stars. No commits in the last 6 months.
Stars
245
Forks
92
Language
C++
License
Apache-2.0
Category
Last pushed
Aug 03, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AlexOlsen/DeepWeeds"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
AutoRoboCulture/Nindamani-the-weed-removal-robot
Nindamani, the AI based mechanically weed removal robot
ricber/digital-agriculture-datasets
Open datasets for training and benchmarking AI and robotic systems in agriculture and off-road...
liaopeiyuan/TransferDet
This is the repository containing team OverFeat's submission to CVPPP 2020's Wheat Detection...
Ildaron/Laser_control
Laser for control mosquito, weed, and pest
B-AROL-O/FREISA
Four-legged Robot Ensuring Intelligent Sprinkler Automation