-
get the following error after upgrading to edward version 1.3.1 and tensorflow version 1.1.0
```sess.run([inference.update], feed_dict=d.train_feed(m.placeholders))
File "/home/maja/.local/lib/py…
-
I'm on` Windows 10 64-bit`, with `Python 3.5` and using `Tensorflow 1.10`. I've set the argument to point the training files and evaluation files correspondingly to local as well according to the guid…
-
One of the simplest and quite popular example of where we need tensors is a derivative of a matrix-matrix multiplication:
```
C = A*B
```
If all three are matrices, then derivative of `C` w.r.t. `A…
-
In my tutorial (version Nov 9, 2016) I identified the following formulas:
Mostly these contain tensor structure or (from my point of view) a more or less missleading
contraction of more than one Na…
joha2 updated
7 years ago
-
### System information
- **What is the top-level directory of the model you are using**: attention_ocr
- **Have I written custom code (as opposed to using a stock example script provided in Tensor…
-
-
Here's the `backend` branch, introducing `theano_backend.py` and `tensorflow_backend.py`: https://github.com/fchollet/keras/tree/backend/keras/backend
It's still a work in progress. It contains 95% o…
-
When I use tensorlayer to train my data,I write
######
"tl.utils.fit(sess, network, train_op, cost, x_train, y_train, x, y_,
acc=acc, batch_size=50, n_epoch=20, print_freq=2,
…
-
I got Keras 1.2.2 and tensorflow 1.0.0 running on a Django server on a Windows 10 machine.
My current architecture loads the weights (load_weights) each time there is a relevant rest API call. Thi…
-
Hello!
I just would like to know if high dimensional matmul will be supported in the future?
For example, I have a 3D tensor a and a matrix b as below:
``` python
a = [[[1,1],
[1,1]],
…