Skip to main content
22 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
1 vote
0 answers
106 views

According to the github page for tensorflow fairness-indicators : Fairness Indicators enables easy computation of commonly-identified fairness metrics for binary and multiclass classifiers. However, ...
Saurabh Verma's user avatar
  • 6,818
1 vote
1 answer
2k views

I'm building a tfx pipeline based on the cifar10 example : [https://github.com/tensorflow/tfx/tree/master/tfx/examples/cifar10] The difference is that I don't want to convert it to tf_lite model and ...
Juan Acevedo's user avatar
  • 1,788
3 votes
0 answers
289 views

I'm not getting tfma.view.render_plot to render plots with: tfma.view.render_plot(result) or tfma.view.render_time_series note that tfma.view.render_slicing_metrics does work.. I suspect it's related ...
Jason Anderson's user avatar
  • 113
0 votes
1 answer
1k views

Basically I only reused code from iris utils and iris pipeline with minor change on serving input: def _get_serve_tf_examples_fn(model, tf_transform_output): model.tft_layer = ...
suisen's user avatar
  • 53
2 votes
1 answer
845 views

I have created a custom Keras metric, similar to the demo implementation below: import tensorflow as tf class MyMetric(tf.keras.metrics.Mean): def __init__(self, name='my_metric', dtype=None): ...
neurix's user avatar
  • 4,356
0 votes
1 answer
626 views

I am training a Keras model using custom training loops in TensorFlow, where the weights are updated using gradient tape rather than the model.fit() method. As such, the model is not compiled before ...
andre's user avatar
  • 41
0 votes
1 answer
2k views

I'm trying to install it on colab notebook. The command I tried is : pip install models It's giving me error as: Collecting models Using cached https://files.pythonhosted.org/packages/92/3c/...
Sonali Jadhav's user avatar
  • 3
1 vote
0 answers
323 views

I have been using bazel build for my im2txt model from TensorFlow and it shows me ModuleNotFoundError: No module named 'nltk' I have installed the package nltk and tried to even create an ...
user avatar
0 votes
1 answer
155 views

I downloaded tfma source code 0.13.2 and ran it in jupyter notebook locally with python2, and it does not work Working code: import tensorflow as tf import third_party.tensorflow_model_analysis....
Zixun Zhang's user avatar
  • 1
2 votes
0 answers
432 views

I am trying to visualize model results using tfma.view.render_slicing_metrics. I am getting the results with tfma.load_eval_result(tfma_artifact.uri) and I am able to print the results. [EvalResult(...
Rathna Subramanian.T.A's user avatar
  • 21
4 votes
1 answer
1k views

I would like to use TFMA with keras model. The keras model was created with TF 2.0 alpha. The model is a pretrained model with a classification layer: ...
eilalan's user avatar
  • 689
3 votes
1 answer
4k views

I'm trying Tensorflow Model Optimization in order to prune a simple Neural Network. Here's my code: from __future__ import absolute_import, division, print_function, unicode_literals, ...
razimbres's user avatar
  • 5,105
7 votes
1 answer
494 views

I am reading the faster-rcnn code of tensorflow models. I am confused with the use of tf.stop_gradient. Consider the following code snippet: if self._is_training: proposal_boxes = tf....
tidy's user avatar
  • 5,127
0 votes
1 answer
311 views

I am trying to follow the guide on this link but I get an error on the second step for enabling TFMA visualization in Jupyter Notebook. I assume this is something you do in a cell?
netskink's user avatar
  • 4,639
2 votes
2 answers
147 views

For example if i want to use renset_v2, there are two model file on tensorflow: one is here, another is here. Lots of tensorflow model are both in models/research and tensorflow/contrib. I am very ...
tidy's user avatar
  • 5,127

15 30 50 per page
1
2