Where communities thrive

  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
  • 06:41
    khs96p edited #1168
  • Nov 12 23:38
    lamberta closed #1137
  • Nov 12 23:35
    TensorFlow-Docs-Copybara closed #1146
  • Nov 12 23:33
    TensorFlow-Docs-Copybara closed #1078
  • Nov 12 21:56
    TensorFlow-Docs-Copybara closed #1138
  • Nov 12 21:41
    lamberta labeled #1136
  • Nov 12 21:36
    lamberta closed #1132
  • Nov 12 21:36
    lamberta closed #1106
  • Nov 12 21:36
    lamberta closed #1149
  • Nov 12 21:35
    lamberta closed #1070
  • Nov 12 21:24
    TensorFlow-Docs-Copybara closed #1083
  • Nov 12 21:00
    TensorFlow-Docs-Copybara closed #1159
  • Nov 12 20:28
    lamberta labeled #1078
  • Nov 12 20:25
    TensorFlow-Docs-Copybara closed #1179
  • Nov 12 20:23
    lamberta labeled #1149
  • Nov 12 20:23
    lamberta synchronize #1149
  • Nov 12 20:22
    lamberta unlabeled #1149
  • Nov 12 20:22
    lamberta closed #1158
  • Nov 12 20:21
    lamberta synchronize #1158
  • Nov 12 20:21
    lamberta unlabeled #1158
Vishesh Mangla
3-4 layers of 30*30 conv gets computed with 10 epochs in 2 mins or so or even faster but why is this so slow?
I 'm using gpu
I tried tpu too
I converted my code fro scipy to tensorflow only for gpu power
because matrices are 1000* 1000 dimensions
Also in tf 2.0 contrib is removed
where can I find integrate.odeint?
@lamberta is non eager still supported in tensorflow 2?
Sean Morgan
So you can decorate eager functions with @tf.function to build a graph representation under the hood. Alternatively public API from TF 1.x is available using tf.compat.v1 https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1
So you can still run sessions/graphs if you really want
def testing():
    model = Sequential([
        Dense(1, activation='sigmoid')
    model.compile('adam', tf.keras.losses.BinaryCrossentropy(), metrics=[tf.keras.metrics.BinaryAccuracy()])

    xs = np.linspace(-1, 1, 100)
    ys = np.where(xs <= 0, 1, 0)
    plt.plot(xs, ys)

    results = model.evaluate(xs, ys)
    print('before training test loss, test acc:', results)
    yps = model.predict(xs)
    print(np.mean(yps), yps[:10].flatten())

    model.fit(xs, ys, batch_size=100, epochs=400, verbose=0)

    results = model.evaluate(xs, ys)
    print('after training, test loss, test acc:', results)
    yps = model.predict(xs)
    print(np.mean(yps), yps[:10].flatten())

This prints 100% accuracy before and after training.
100/100 [==============================] - 0s 1ms/sample - loss: 0.4602 - binary_accuracy: 1.0000
before training test loss, test acc: [0.4602195370197296, 1.0]
0.49999997 [0.75605214 0.7518128  0.7475245  0.7431873  0.73880166 0.7343679
 0.72988635 0.72535753 0.7207818  0.7161597 ]
100/100 [==============================] - 0s 137us/sample - loss: 0.2889 - binary_accuracy: 1.0000
after training, test loss, test acc: [0.28886041820049285, 1.0]
0.50000006 [0.9287006  0.9251896  0.92152035 0.91768706 0.9136842  0.90950584
 0.90514624 0.9005994  0.89585984 0.8909216 ]
Well it does SOMETIMES
@lamberta I think this example is very poor https://www.tensorflow.org/guide/datasets#using_high-level_apis
filenames = ["/var/data/file1.tfrecord", "/var/data/file2.tfrecord"]
dataset = tf.data.TFRecordDataset(filenames)
dataset = dataset.map(...)
dataset = dataset.shuffle(buffer_size=10000)
dataset = dataset.batch(32)
dataset = dataset.repeat(num_epochs)
iterator = dataset.make_one_shot_iterator()

next_example, next_label = iterator.get_next()
loss = model_function(next_example, next_label)

training_op = tf.train.AdagradOptimizer(...).minimize(loss)

with tf.train.MonitoredTrainingSession(...) as sess:
  while not sess.should_stop():
1) The label is given to the model and the loss is calculated inside the model function.
2) There is no evaluate operation so training progress is not printed.
3) The number of epochs is fixed and decided by repeating the dataset instead of in the training loop.
The documentation https://www.tensorflow.org/api_docs/python/tf/keras/layers/LayerNormalization says that you can give a tuple as input to axis
but the code tries to manipulate the elements of self.axis which doesn't work since tuples are immutable
I created an issue tensorflow/tensorflow#32311
has it been removed?
now tf.config.optimizer_set_jit(True) gives an error saying AttributeError: module 'tensorflow._api.v1.config' has no attribute 'optimizer_set_jit'
Billy Lamberta
@HarikrishnanBalagopal Good question. Can you ask the XLA list? https://groups.google.com/forum/#!forum/xla-dev May need a doc update
Is there a possibility to have rectified ADAM in TensorFlow ?
PyTorch has already the implementation done.
Sean Morgan
RAdam should be available in tensorflow/addosn within a week or two:
thanks very much.
Pytorch have already it.... for months...so
Sean Morgan
The initial code from the paper's author was in PyTorch so makes sense to me. Not sure what your intentions are for baiting here but this is an open source community and many of us work for free... Have a nice day :)
Is there any offline documentation for zeal's tf2.0.0 stable version? My network environment is too bad.
Billy Lamberta
@miffyrcee Hello. The source notebooks and markdown for the TF2 guides/tutorials are in the tensorflow/docs GitHub repo—which you can download: https://github.com/tensorflow/docs/tree/master/site/en
You can select the branch to see the Markdown API docs. Though, looks like we still need to add the TF2 ref docs. Will work on that, thanks :)
@lamberta Ok! Thanks a lot.I will try a later.
hi i have a question about how to assign eagerTensor slice value? prediction[:,:,0]=tf.math.sigmoid(prediction[:,:,0]) will raise exception
'tensorflow.python.framework.ops.EagerTensor' object does not support item assignment
Sean Morgan
You would want a tf.Variable if you want a mutable object
Tensors are produced values from computations
Mohammed Sharuk
Hey guys,I'm new to gitter chat platform
I have an idea that integrates with the tensorflow's tensorboard.Does anyone know how to contribute my idea to the tensorboard???
Billy Lamberta
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
Mohammed Sharuk
Thanks,will check this out
Reuben Morais
hello y'all. I can't find the docs' source for 1.15 or 2.0 stable on the repo, did they get migrated somewhere else for these releases?
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?
Sayak Paul
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:


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

Quick question:
How to address issues like this:tensorflow/tensorflow#34002
Also, I did reply to the message but was wondering if it's not very helpful, can this be closed?