-
**Describe the bug**
prune_low_magnitude cannot reduce the size of tflite model. I run the pruning with keras example (https://github.com/tensorflow/model-optimization/blob/master/tensorflow_model_…
-
ghost updated
6 years ago
-
@jatentaki thanks for the code. I was wondering if this code achieves similar performance with `hnet` on `rotmnist`. Compared to the work of Worrall et al where they get 98.5%, I get only around 94% w…
-
I build the following model
```model = Sequential([
InputLayer(input_shape=[1, 28, 28]),
Conv2D(6, kernel_size=[3, 3], activation='relu', padding='same', data_format='channels_first'),
…
ghost updated
7 years ago
-
I have followed the installation instructions but am having a problem during training.
When I run
`python ./train.py`
the line
`network = conv_2d(network, 8, [5, 3], activation='relu')`
throws the …
-
**System information**
- Have I written custom code (as opposed to using a stock example script provided in TensorFlow): Using TF-Java
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): macO…
-
A tool for MLP training should be added.
Before this can be tackled, issue #3 has to be solved.
-
Hi,
I have used the train-a-digit-classifier in a CPU mode and it is worked well. but now I want to test it in a GPU mode. I have a NVIDIA JETSON TK1 where I have installed CUDA 6.5 and all other pr…
-
Hi there!
This is a really cool library and I'm excited to try it out (especially after spending several hours fighting my environment to get tch-rs working >_> - still haven't, suspect it's easier…
-
Question: How do I get the embeddings after fitting using triplet loss in this example: https://mlverse.github.io/luz/articles/examples/mnist-triplet.html ?