He Ma
He Ma
Is there a way to interpolate/extrapolate the latent space? In order to see the distribution near the inferenced image y given input image x and condition label c. Will interpolating...
According to the [Facebook paper](https://arxiv.org/pdf/1706.02677.pdf), there are several implementation details to be adjusted: - [x] 1. Momentum correction. In our implementation, we used the equation (10) without momentum correction. We...
When running the train.py code. I got lots of FutureWarning like the following. This might be due to a numpy update from the version this project was based on. ```...
As mentioned in #19 [here](https://github.com/uoguelph-mlrg/theano_alexnet/issues/19#issuecomment-147700903). I think we need to do the preprocessing with respect to the aspect ratio of the image like pytorch is doing [here](https://github.com/pytorch/vision/blob/master/torchvision/transforms.py#L187-L197). Instead of simply...
The step_idx should be changed if using pre-trained weight for resuming training state. For example, add `step_idx = epoch / 20` after the following line: https://github.com/uoguelph-mlrg/theano_alexnet/commit/23440c6ece43e0551fa978ab7bf257d71de4b5e1#diff-e44f4a60e89e820dde9bb27afa634965R98 The same part in...
Add RGB regularization on image pixels to make the Neural Network invariant to changes in the intensity and color of the illumination. First, run python get_cov_matrix.py to generate the RGB...
有TVB女声 吗
这个配音貌似比较popular，不知道怎么训练出来的
Hi, I want to reproduce the comparison between A3C and GA3C in Table 2 in your paper. I wonder if the A3C experiment can be done using this repo? Thanks
Can we have some control on how large is the overlay button is? It is blocking a bit area of the phone screen and I find it useful to be...