-
__For test_lstm:__
1. keras give the same output for both ubuntu and Mac
2. The output of BigDL is the same with Keras on Ubuntu
3. The output of BigDL on Mac is wrong if we suppose the output on U…
-
I am trying to fit a time series of a chaotic system with a 3 state hidden markov model with gaussian emissions. I format the data as a numpy array called input_data, and run the code below:
`
```…
-
Just like the title "the successful rate of attacking example of ImagetNet datasets is so low with DeepFoolAttack" which is tested with the following code:
```
#get the dict of label
ff = open(".…
-
Hi, after running an example in readme I get:
```
AttributeErrorTraceback (most recent call last)
in ()
8 kmodel = ResNet50(weights='imagenet')
9 preprocessing = (numpy.array([104,…
-
I'm wondering about the default parameters for the lbfgs attack.
When I use the example code to attack an image with lbfgs, I get much worse results in terms of distance from adversarial to real, co…
neale updated
7 years ago
-
So basically i am training a doc2vec model. I came across something called get_embedding_layer in KeyedVectors class which returns a embedding layer. But I am unable to retrieve the weights for this l…
-
I tried on two different machines with g++ 4.8 and g++ 5.4 and the result was same.
I downloaded the latest code from github and built using cmake. My application code is throwing following error e…
-
It is a feature or a bug?
For example, I have 2 models:
typical imports:
```
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorf…
-
Hi, I'm trying to follow along the post below utilizing keras, with tensorflow backend.
https://aboveintelligent.com/face-recognition-with-keras-and-opencv-2baf2a83b799
Combined with the noteboo…
-
@esheldon and I have been discussing some ways that the k-space rendering in GalSim could be sped up. One of the ideas is to use faster exp and invsqrt functions when possible. We have parameters xv…