-
In the paper, in figures 1 and appendix C.4 you describe rotated MNIST experiments, but those don't appear present in the codebase. Were these done using a different codebase, or has the code not been…
-
Hi,
I was interested in trying to train a FIF on MNIST down to a latent dimensionality of 128, or even 12 to compare the compression.
I am using an encoder/decoder, similar to Table 11: https://ar…
-
In Lab2-Computer-Vision.ipynb, which is about Fashion-MNIST, there's this line:
> the first value in the list is the probability that the handwriting is of a '0', the next is a '1' etc.
Which i…
-
Don't forget about array programming
https://github.com/bones-ai/odin-mnist-nn/blob/eb32f633d242f827d43407a02382af2f60426736/viz.odin#L205-L209
```odin
shape_pos = (s.start + s.end)/2
```
-…
-
[Result][Early Stop][Optimal Layer Detected] opt_layer=0, accuracy_train=18.0000%, accuracy_test=21.0000%.
-
I am trying to replicate the MNIST classification experiment through ECC by following the model configuration reported in your paper. There are some issues that I was not able to solve:
1 - the descr…
-
For some reason, BN is not really helping ( in fact, NN using BN has worse performance than the ones not using BN). Will further investigate why.
msyim updated
7 years ago
-
The notebook returns an error when try to use the display_digits() because the parameter b of grid was deprecated in [matplotlib 3.5](https://matplotlib.org/stable/api/prev_api_changes/api_changes_3.5…
-
### Search before asking
- [X] I searched the [issues](https://github.com/ray-project/ray/issues) and found no similar issues.
### Ray Component
Ray Tune
### What happened + What you exp…
-
[test.txt](https://github.com/deepmind/dm-haiku/files/11395424/test.txt)
I use LSTM to classify mnist data and find that the loss of the network cannot converge at all. Is the RNN given by the framew…