A Python package for identifying 42 kinds of animals, training custom models, and estimating distance from camera trap videos
Bug fixes for docs
VIDEO_CACHE_DIR
environment variable is an empty string or zero (PR #245)time_distributed
model (African species classification) has been retrained on over 250,000 videos. This 16x increase in training data significantly improves accuracy. This new version replaces the previous one. (PR #226, PR #232)blank_nonblank
. This model only does blank detection. This binary model can be trained and finetuned in the same way as the species classification models. This model was trained on both African and European data, totaling over 263,000 training videos. (PR #228)instantiate_model
for clarity (PR #229)model_name
based on the provided checkpoint so that user-trained models use the appropriate video loader config (PR #221)data_dir
as a relative path (PR #219)get_cached_array_path
(PR #202)