Domenick Poster

icon indicating an email [email protected]

icon company West Virginia University icon location Baltimore, MD icon location PhD in computer science / computer vision / deep learning

Results 3 issues of Domenick Poster

Changed LDA Feature class to handle non-continuous sets of class labels

Before, class labels were assumed to be {0,1,2,3,..., n}. Now, labels may be {1, 3, 7, ..., n}. I found myself needing to train and test on subsets of my...

Error generating tfdata_12net

4 comment

After running `gen_shuffle_data.py`, I get 644,000 negative samples. https://github.com/wangbm/MTCNN-Tensorflow/blob/4ae3a720dc08aebb107f9ed0335c7b0b5e3e22c6/prepare_data/gen_tfdata_12net.py#L77 generates an error because I cannot sample 1,000,000 times without replacement from a pool of 644,000. Is this intended to be...

[Bug/Task]: Error in implementation of GANomaly's generator loss

### Describe the bug The GANomaly paper and original implementation (https://github.com/samet-akcay/ganomaly/blob/master/lib/model.py#L318) use the feature representations of the discriminator for the generator's adversarial loss component. This makes sense as the generator's...