tensorflow - w3toppers.com

How do I split Tensorflow datasets?

You may use Dataset.take() and Dataset.skip(): train_size = int(0.7 * DATASET_SIZE) val_size = int(0.15 * DATASET_SIZE) test_size = int(0.15 * DATASET_SIZE) full_dataset = tf.data.TFRecordDataset(FLAGS.input_file) full_dataset = full_dataset.shuffle() train_dataset = full_dataset.take(train_size) test_dataset = full_dataset.skip(train_size) val_dataset = test_dataset.skip(test_size) test_dataset = test_dataset.take(test_size) For more generality, I gave an example using a 70/15/15 train/val/test split but if you don’t … Read more

Get the value of some weights in a model trained by TensorFlow

In TensorFlow, trained weights are represented by tf.Variable objects. If you created a tf.Variable—e.g. called v—yourself, you can get its value as a NumPy array by calling sess.run(v) (where sess is a tf.Session). If you do not currently have a pointer to the tf.Variable, you can get a list of the trainable variables in the … Read more

Understanding TensorBoard (weight) histograms

It appears that the network hasn’t learned anything in the layers one to three. The last layer does change, so that means that there either may be something wrong with the gradients (if you’re tampering with them manually), you’re constraining learning to the last layer by optimizing only its weights or the last layer really … Read more

Module ‘tensorflow’ has no attribute ‘contrib’

tf.contrib has moved out of TF starting TF 2.0 alpha. Take a look at these tf 2.0 release notes https://github.com/tensorflow/tensorflow/releases/tag/v2.0.0-alpha0 You can upgrade your TF 1.x code to TF 2.x using the tf_upgrade_v2 script https://www.tensorflow.org/alpha/guide/upgrade

What is the meaning of the “None” in model.summary of KERAS?

None means this dimension is variable. The first dimension in a keras model is always the batch size. You don’t need fixed batch sizes, unless in very specific cases (for instance, when working with stateful=True LSTM layers). That’s why this dimension is often ignored when you define your model. For instance, when you define input_shape=(100,200), … Read more

Can I use TensorBoard with Google Colab?

EDIT: You probably want to give the official %tensorboard magic a go, available from TensorFlow 1.13 onward. Prior to the existence of the %tensorboard magic, the standard way to achieve this was to proxy network traffic to the Colab VM using ngrok. A Colab example can be found here. These are the steps (the code … Read more

How Can I Define Only the Gradient for a Tensorflow Subgraph?

Here’s a trick from Sergey Ioffe: Suppose you want group of ops that behave as f(x) in forward mode, but as g(x) in the backward mode. You implement it as t = g(x) y = t + tf.stop_gradient(f(x) – t) So in your case your g(x) could be an identity op, with a custom gradient … Read more

How to set specific gpu in tensorflow?

There are 3 ways to achieve this: Using CUDA_VISIBLE_DEVICES environment variable. by setting environment variable CUDA_VISIBLE_DEVICES=”1″ makes only device 1 visible and by setting CUDA_VISIBLE_DEVICES=”0,1″ makes devices 0 and 1 visible. You can do this in python by having a line os.environ[“CUDA_VISIBLE_DEVICES”]=”0,1″ after importing os package. Using with tf.device(‘/gpu:2’) and creating the graph. Then it … Read more

What is the meaning of the word logits in TensorFlow? [duplicate]

Logits is an overloaded term which can mean many different things: In Math, Logit is a function that maps probabilities ([0, 1]) to R ((-inf, inf)) Probability of 0.5 corresponds to a logit of 0. Negative logit correspond to probabilities less than 0.5, positive to > 0.5. In ML, it can be the vector of … Read more

How does TensorFlow name tensors?

Your observations on Tensor naming are absolutely correct: the name of a Tensor is the concatenation of the name of the operation that produced it, a colon (:), and the index of that tensor in the outputs of the operation that produced it. Therefore the tensor named “foo:2” is the output of the op named … Read more