An open API service providing repository metadata for many open source software ecosystems.

GitHub / sraddhanjali / Aerial-Cactus-Identification

Trained a CNN model to classify cactus species (columnar cactus) in a binary classification challenge, hosted on Kaggle competition. Refined the model with image augmentation, pre-trained VGG16 model parameters using transfer learning, and improved the identification metric (area under ROC score) from 0.9964 to 0.9971 on the test set.

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sraddhanjali%2FAerial-Cactus-Identification
PURL: pkg:github/sraddhanjali/Aerial-Cactus-Identification

Stars: 0
Forks: 0
Open issues: 10

License: None
Language: Jupyter Notebook
Size: 3.56 MB
Dependencies parsed at: Pending

Created at: about 6 years ago
Updated at: over 1 year ago
Pushed at: almost 3 years ago
Last synced at: over 1 year ago

Topics: classification, image-classification, transferlearning, vgg16-model

    Loading...