Oleg Zabluda's blog
Tuesday, October 18, 2016
 
Open Sourcing a Deep Learning Solution for Detecting NSFW Images
Open Sourcing a Deep Learning Solution for Detecting NSFW Images
"""
The deep models were first pre-trained on the ImageNet 1000 class dataset. For each network, we replace the last layer (FC1000) with a 2-node fully-connected layer. Then we fine-tune the weights on the NSFW dataset. Note that we keep the learning rate multiplier for the last FC layer 5 times the multiplier of other layers, which are being fine-tuned. We also tune the hyper parameters (step size, base learning rate) to optimize the performance.

We observe that the performance of the models on NSFW classification tasks is related to the performance of the pre-trained model on ImageNet classification tasks, so if we have a better pretrained model, it helps in fine-tuned classification tasks. The graph below shows the relative performance on our held-out NSFW evaluation set.
[...]
We are releasing the thin ResNet 50 model, since it provides good tradeoff in terms of accuracy, and the model is lightweight in terms of runtime (takes < 0.5 sec on CPU) and memory (~23 MB).
"""
https://yahooeng.tumblr.com/post/151148689421/open-sourcing-a-deep-learning-solution-for

https://github.com/yahoo/open_nsfw
https://yahooeng.tumblr.com/post/151148689421/open-sourcing-a-deep-learning-solution-for

Labels:


- posted by Oleg Zabluda @ 3:40 PM | permalink | | | technorati | bloglines | feedster
| |

Home

Powered by Blogger