Gant Laborde
Gant Laborde
Thanks for reporting this. I'll add this image and images like this to the training set.
That's a good question. My guess is that manga wasn't properly represented in the training set. However, the model is set to have more false positives, than false negatives. Because...
Hi! I'm not sure I understand the question. > I just wanted to know how can I compile these models from graph to image (299x299)? I know I can just...
The size option depends on the model you load. You won't be able to use the graph with 299, because it was trained on 224 data. That is a lot...
Hiya! So `train_fine_tune.py` unlocks more of the core model layers for training. https://github.com/GantMan/nsfw_model/blob/master/training/inceptionv3_transfer/train_fine_tune.py#L24-L33 As I understand it, if you unlocked all the layers and started base weights, you'd have to...
We began work on something for this. It is unfortunately a lot a lot of work. Can you identify what the need for such a feature might be?
That makes sense. To be honest, the amount of work needed to make that would be substantial. Would this be a model you'd be willing to pay for?
We charge 6k USD a week of work. I honestly don't know how long it would take. We have 2k labeled object detection images right now, but we'd need to...
Can you specify what size/link to the model you're using? Maybe email me the images that it is failing on? Are you sure this is for all NSFW images? Or...
Can you provide the failing issues?