-
first of all, thx for implementation!
the question is about proper masking inside the model
1. shift_down and shift right in the beginning of PixelSnail module have already taken care of masking…
-
I'm pretty sure the log-likelihood for the solution to the second exercise is off. The nll is defined as:
```
def nll(self, x, cond=None):
loc, log_scale, weight_logits = torch.chunk(self.f…
-
In file nn.py:
Could anybody help me out explain why here is + 1./255. not 0.5 as paper equation (2) ?
```
60. centered_x = x - means
61. inv_stdv = tf.exp(-log_scales)
62. plus_in = inv…
-
# Flexible conditional density estimators for discrete data
Neural conditional density estimators such as MDNs and MAFs are great for continuous data, but often we run into discrete distributions (…
-
when training to cifar,it consist to increasing costed memory and do not begin to train.
I have a 2*16G RAM.It's seem to be enough.
1*GTX1080
cudnn6
tensorflow1.4
python3.5
-
Hi, thank you for this TensorFlow implementation of PixelCNN.
When I try to use images of size 64x64x3, the TensorFlow graph compiles without errors but the training does not start. The only thing …
-
Observations:
1. The reconstruction image is not good.
2. In the current code, the training procedure is very unstable.
3. The dictionary loss (the commitment loss) decreases initially, but signi…
-
Hey there,
I'm doing my masters degree on Sonic Arts and trying to come up with a good thesis on applications of machine learning on audio. I've been playing around with magenta and wavenet (thanks…
-
Trying to initialize an instance of `tfb.AutoregressiveNetwork` using the jax substrate fails with an AttributeError.
With the example usage from the [docs](https://www.tensorflow.org/probability/a…
-
The following pattern is common is user code and our examples:
```
def shard(pytree, n_devices):
def _shard_array(array):
return array.reshape((n_devices, -1) + array.shape[1:])
return ja…