-
I would like sklearn to support Poisson, gamma and other Tweedie family loss functions. These loss distributions are widely used in industry for count and other long tailed data. Additionally, they ar…
-
1. Image-to-Image Translation with Multi-Path Consistency Regularization
https://arxiv.org/pdf/1905.12498.pdf
2. Mask-Guided Portrait Editing with Conditional GANs
https://arxiv.org/pdf/1905.10346.…
-
Hi @Fezaries , thanks for your nice codes. In your paper, you use a different alpha and beta. Would you mind to let me know how do you tune these two parameters?
D-X-Y updated
5 years ago
-
I think it would be useful to collect user experience / discuss / get some help about the high-level meaning / use of the PPO meta-parameters.
This may be a more general discussion than just tensor…
-
Dear Dr. Dalca,
I'm sorry to bother you again. Recently, I am working on the stationary velocity field integration method, I notice that you mentioned 3 methods, including scaling and squaring, quadr…
-
arXiv论文跟踪
-
hello nick
while testing your code I noticed the processing time at each scale.
on the example I'm working on :
scl1 (long side 64): 250 iters takes 87s
scl2 (long side 128): 250 iters takes 63s
…
-
I have tried to reproduce several of Caffe's example codes, but the accuracy in Keras consistently seems to fall a few percent behind with the convolutional architectures. For example, here is a sligh…
dnola updated
5 years ago
-
I try to add l2 regularizer for tf.keras.layers.CuDNNLSTM, here is my code for creating layers:
```
regulizer = tf.keras.regularizers.l2(l=1)
net = tf.keras.layers.CuDNNLSTM(lstm_units…
-
**Describe the bug**
I am running the Criteo example, documented[ here](https://cloud.google.com/blog/products/gcp/using-google-cloud-machine-learning-to-predict-clicks-at-scale). I can run the prepr…