Tensors are produced values from computations
I have an idea that integrates with the tensorflow's tensorboard.Does anyone know how to contribute my idea to the tensorboard???
Hi @mhdSharuk, there is a SIG TensorBoard you might be interested in: https://groups.google.com/a/tensorflow.org/d/forum/sig-tensorboard
They also have community meetings
They also have community meetings
ah, I guess for 2.0 they're supposed to be generated from the installed package version
but will that also work for 1.15?
Has anyone tried to visualize what a VAE as shown here (https://www.tensorflow.org/beta/guide/keras/custom_layers_and_models#putting_it_all_together_an_end-to-end_example) learned?
I tried it in this notebook: https://colab.research.google.com/drive/1LhIUA8_XbMd1gF2xGFB_50FLHoebY0MK. I found that the VAE was learning an average representation of the inputs fed to it.
I think adding this kind of visualization actually helps in many cases. In this case, we can clearly see that the model might require longer training and a bit of hyperparameter tuning (KLD factor specifically).
The above suggestion was shared by Francois himself, though. So, what I am suggesting here is incorporating helper function that lets you visualize the representation the VAE learned.
The following might be helpful:
##########################
### VISUALIZATION
##########################
n_images = 15
image_width = 28
fig, axes = plt.subplots(nrows=2, ncols=n_images,
sharex=True, sharey=True, figsize=(20, 2.5))
orig_images = x_batch_train[:n_images].numpy()
decoded_images = reconstructed[:n_images].numpy()
for i in range(n_images):
for ax, img in zip(axes, [orig_images, decoded_images]):
curr_img = img[i]
ax[i].imshow(curr_img.reshape((image_width, image_width)), cmap='binary')Courtesy: Sebastian Raschka
Also, I did reply to the message but was wondering if it's not very helpful, can this be closed?
They also don't seem to follow code of conduct
@lamberta I have been trying to work with docker for tensorflow (https://www.tensorflow.org/install/docker) and I feel some information on documentation may be helpful. One big add-o could be the examples. Few times, the user is directed to https://docs.docker.com/engine/reference/run/ but currently trying to work with docker, I felt a few additions in the documentation could help someone new to docker and trying to work with TensorFlow, a lot. I do find my clarifications on stack overflow, but some additions to the docs may help save time for others. Do you think it is something worth contributing?
@copperwiring Sure! That file is here: https://github.com/tensorflow/docs/blob/master/site/en/install/docker.md
Please send a PR if you think it clarifies. I'd like to avoid it becoming a Docker tutorial so if we can link off to their material for deep dives, I think that's best. But feel free to surface relevant details if you think it helps.
(thanks for the pointer to the other PR, i've passed it along to the Issue maintainers)
Please send a PR if you think it clarifies. I'd like to avoid it becoming a Docker tutorial so if we can link off to their material for deep dives, I think that's best. But feel free to surface relevant details if you think it helps.
(thanks for the pointer to the other PR, i've passed it along to the Issue maintainers)
Hello! I am confused about the documentation for TPU Pods. So far I have found this one - https://cloud.google.com/tpu/docs/training-on-tpu-pods and not much else. Is there anything I am missing?
@rd16395p You're not missing anything :/
TF 2.1 will be more TPU-focused release. So, ideally, you'll see these docs under our dist strat guide and tutorials.
Though, generally, the TF TPU repo is the best thing to watch for active updates: https://github.com/tensorflow/tpu
TF 2.1 will be more TPU-focused release. So, ideally, you'll see these docs under our dist strat guide and tutorials.
Though, generally, the TF TPU repo is the best thing to watch for active updates: https://github.com/tensorflow/tpu
@rd16395p Depends on the scope of the doc. If you have an idea, proposal, or even just want clarification, can you file an issue on the tf/tpu repo? https://github.com/tensorflow/tpu/issues
Tag me in and I can probably loop some folks in
Tag me in and I can probably loop some folks in
Oh cool. Well, if you want to start one, you can put it in the community section: https://github.com/tensorflow/examples/tree/master/community/en
But given the emphasis on TPUs in TF 2.1, I suspect this should be integrated into the main docs---wherever they end up
But given the emphasis on TPUs in TF 2.1, I suspect this should be integrated into the main docs---wherever they end up
I just haven't seen a way to make a notebook work with a tpu pod connection.
Hello, I am back and I got this example (https://github.com/tensorflow/tpu/tree/master/models/samples/core/get_started) to work on the pod. Where should I put this one? Is it the same place?
@rd16395p Nice work! Yes, a PR to the same place is probably best for now. Did you need to change a lot? By that I mean, is it worth having a separate tutorial to show what you did to configure the pod, or is it just a line or two of configuration that can be called out in the current tutorial?
I made my own sort of area here - https://github.com/rd16395p/TPU-Pod-Examples
Hey there, I want to edit the doc for https://www.tensorflow.org/api_docs/python/tf/bitcast . But it is 'Defined in generated file:
python/ops/gen_array_ops.py'.
Any idea on how to proceed.
@kshitijaggrwl , if you want to contribute to the documentation, please go through these guidelines: https://www.tensorflow.org/community/contribute/docs
