Training Details (Skip this part if you arent interested in AI programming) - I used 2000 synthetic 512x512 px training images (plus 200 synthetic validation images) - I did ZERO training on real images - I trained the "heads" for 4 epochs of 500 steps and the full network for another 4 epochs - Resnet50 backbone (Resnet101 caused OOM errors) using COCO pre-trained weights - Training took about 20 minutes on my computer - Final losses after the 8th epoch: loss: 0.3615 - rpn_class_loss: 0.0023 - rpn_bbox_loss: 0.1823 - mrcnn_class_loss: 0.0232 - mrcnn_bbox_loss: 0.0636 - mrcnn_mask_loss: 0.0901 - val_loss: 0.3261 - val_rpn_class_loss: 0.0013 - val_rpn_bbox_loss: 0.1875 - val_mrcnn_class_loss: 0.0043 - val_mrcnn_bbox_loss: 0.0535 - val_mrcnn_mask_loss: 0.0794 Results It's far from perfect, and probably isn't practical to bolt onto a robot right now, but with more training and improvements in GPU hardware, I think this could be a viable solution to pick up cigarette butts on a huge scale
The low price point further drives adoption
1 While there are many smoking cessation tools availablefrom FDA-approved medications to behavioral supportnicotine electronic cigarettes (e-cigarettes) are increasingly being considered as a promising alternative for traditional smokers seeking to quit
Apparently, he previously worked/trained under the watchful eye of one of the greatest perfumers of modern times: Mr Jean-Claude Ellena (formerly the in-house perfumer for Herms )
Some experts also think heavy regulation could halt innovation, deterring manufacturers from creating more advanced devices with better nicotine delivery systems that could help reduce smoking
An epidemiologic review of marijuana and cancer: an update
