Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • 00:41
    lamberta labeled #1206
  • 00:41
    lamberta unlabeled #1206
  • 00:41
    lamberta synchronize #1206
  • 00:32
    lamberta labeled #1206
  • 00:30
    lamberta synchronize #1206
  • Dec 10 22:45
    codeadmin-peritiae synchronize #1256
  • Dec 10 21:17
    codeadmin-peritiae synchronize #1256
  • Dec 10 15:53
    googlebot labeled #1277
  • Dec 10 15:53
    googlebot unlabeled #1277
  • Dec 10 15:48
    googlebot labeled #1277
  • Dec 10 15:48
    SmileTM review_requested #1277
  • Dec 10 15:48
    SmileTM review_requested #1277
  • Dec 10 15:48
    SmileTM opened #1277
  • Dec 10 15:48
    SmileTM review_requested #1277
  • Dec 10 02:18
    googlebot labeled #1276
  • Dec 10 02:18
    tfdocsbot labeled #1276
  • Dec 10 02:18
    tfdocsbot labeled #1276
  • Dec 10 02:18
    masa-ita opened #1276
  • Dec 10 02:18
    masa-ita review_requested #1276
  • Dec 10 02:18
    masa-ita review_requested #1276
HarikrishnanBalagopal
@HarikrishnanBalagopal
during debugging
>l
      8 def f(a):
      9   pdb.set_trace()
---> 10   tf.print(a)
     11   if a > 0:
     12     tf.print('is positive')
where did the extra tf.print(a) line come from?
HarikrishnanBalagopal
@HarikrishnanBalagopal
@lamberta ok I figured it out, you can't use for i in range(64): or something like that since its python objects
you have to use for i in tf.range(64): for it to get converted to tf ops by @tf.function
Billy Lamberta
@lamberta
nice. might be worth a PR to those tf.function docs
HarikrishnanBalagopal
@HarikrishnanBalagopal
with that fix it no longer goes into an infinite loop
while loop also seems to work
@lamberta where tho
it also already kind of mentioned in the docs
Key Point: Only statements that are conditioned on, or iterate over, a TensorFlow object such as tf.Tensor, are converted into TensorFlow ops.
HarikrishnanBalagopal
@HarikrishnanBalagopal
@lamberta are there any plans to add a simple way to release GPU memory?
I have a lot of tests for functions that build networks. These tests create temporary networks, run them once and finish
However looking in tensorboard and also at GPU memory usage in google colab, the memory is not getting released
TruongSinh Tran-Nguyen
@truongsinh
Noobs question, how can I generate HTML for https://github.com/tensorflow/docs locally? python3 setup.py build only generate egg file
Reuben Morais
@reuben
@truongsinh you can't, you can only build markdown but then you have to render it yourself. I built some simple tooling around it for creating docsets, maybe it'll be useful for you:
it doesn't look nearly as refined as the official docs though, for that you'll have to scrape the website
TruongSinh Tran-Nguyen
@truongsinh
thanks @reuben, I'll check it out
TruongSinh Tran-Nguyen
@truongsinh
@reuben is that tool only for API docs? Can I use it for community translation docs like guides and tutorials?
Reuben Morais
@reuben
@truongsinh I only tested it for API docs, not sure if the other sub projects have the same structure
TruongSinh Tran-Nguyen
@truongsinh
gotcha
Vishesh Mangla
@XtremeGood
image.png
I have been waiting for more than 10 mins and this isn't still complete. If it was a neural neutral the computations were definitely faster. What's the reason? Also only a little chunk of ram is being used
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
Vishesh Mangla
@XtremeGood
where can I find integrate.odeint?
HarikrishnanBalagopal
@HarikrishnanBalagopal
@lamberta is non eager still supported in tensorflow 2?
Sean Morgan
@seanpmorgan
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
HarikrishnanBalagopal
@HarikrishnanBalagopal
def testing():
    model = Sequential([
        Input(shape=(1,)),
        Dense(2),
        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())

testing()
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 ]
HarikrishnanBalagopal
@HarikrishnanBalagopal
Well it does SOMETIMES
HarikrishnanBalagopal
@HarikrishnanBalagopal
@lamberta I think this example is very poor https://www.tensorflow.org/guide/datasets#using_high-level_apis
HarikrishnanBalagopal
@HarikrishnanBalagopal
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():
    sess.run(training_op)
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.
HarikrishnanBalagopal
@HarikrishnanBalagopal
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
HarikrishnanBalagopal
@HarikrishnanBalagopal
I created an issue tensorflow/tensorflow#32311
HarikrishnanBalagopal
@HarikrishnanBalagopal
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
@lamberta
@HarikrishnanBalagopal Good question. Can you ask the XLA list? https://groups.google.com/forum/#!forum/xla-dev May need a doc update
gumnn
@arita37
Is there a possibility to have rectified ADAM in TensorFlow ?
PyTorch has already the implementation done.
Sean Morgan
@seanpmorgan
RAdam should be available in tensorflow/addosn within a week or two:
tensorflow/addons#422