tensorboard | 易学教程

Keras: use Tensorboard with train_on_batch()

阅读更多关于 Keras: use Tensorboard with train_on_batch()

问题 For the keras functions fit() and fit_generator() there is the possibility of tensorboard visualization by passing a keras.callbacks.TensorBoard object to the functions. For the train_on_batch() function there obviously are no callback available. Are there other options in keras to create a Tensorboard in this case? 回答1: A possible way to create the TensorBoard callback, and drive it manually: # This example shows how to use keras TensorBoard callback # with model.train_on_batch import

How to use tensorboard Embedding Projector? [closed]

阅读更多关于 How to use tensorboard Embedding Projector? [closed]

问题 Closed. This question is off-topic. It is not currently accepting answers. Want to improve this question? Update the question so it's on-topic for Stack Overflow. Closed last year . How do I use the Embedding Projector included in Tensorboard? I can't find any documentation for it. There are some references to it here, but there's no step-by-step example/tutorial on how to use it. 回答1: As far as I am aware this is the only documentation about embedding visualization on the TensorFlow website.

Unable to use summary.merge in tensorboard for separate training and evaluation summaries

阅读更多关于 Unable to use summary.merge in tensorboard for separate training and evaluation summaries

I am trying to use tensorboard to watch the learning of a convolutional neural net. I am doing good with the tf.summary.merge_all function to create a merged summary. However, I would like to have tracking on accuracy and loss both for training and test data. This post is useful: Logging training and validation loss in tensorboard . To make things easier to handle, I would like to merge my summaries into two merged summaries, one for training and one for validation.(I will add more stuff eventually, like images weights etc.) I tried to follow the description from tensorboard tf.summary.merge .

How to use Keras TensorBoard callback for grid search

阅读更多关于 How to use Keras TensorBoard callback for grid search

问题 I'm using the Keras TensorBoard callback. I would like to run a grid search and visualize the results of each single model in the tensor board. The problem is that all results of the different runs are merged together and the loss plot is a mess like this: How can I rename each run to have something similar to this: Here the code of the grid search: df = pd.read_csv('data/prepared_example.csv') df = time_series.create_index(df, datetime_index='DATE', other_index_list=['ITEM', 'AREA']) target

What's the best way to refresh TensorBoard after new events/logs were added?

阅读更多关于 What's the best way to refresh TensorBoard after new events/logs were added?

What is the best way to quickly see the updated graph in the most recent event file in an open TensorBoard session? Re-running my Python app results in a new log file being created with potentially new events/graph. However, TensorBoard does not seem to notice those differences, unless restarted. It turns out that TensorBoard backend refreshes the logs every minute. This has been reported as a TensorFlow issue . The reload interval can be configured using the --reload_interval flag of the TensorBoard process, but this option is currently only available in master and as of version 0.8 has not

Mobilenet SSD architecture: Downloaded vs trained

阅读更多关于 Mobilenet SSD architecture: Downloaded vs trained

The model zoo of Tensorflow's object detection API provides a bunch of pre-trained models that are ready to be downloaded here . I'm currently looking at ssd_mobilenet_v1_coco. I can quickly obtain the computational graph of the model by running Tensorboard on the event file (see figure below) However, if I train the model from scratch on the coco dataset and run Tensorboard on the event file obtained from the checkpoint, I get a computational graph that looks very different (although it has some similarities): 1) the entire graph appears to have been expanded by default, 2) the variable scope

How to extract and save images from tensorboard event summary?

阅读更多关于 How to extract and save images from tensorboard event summary?

问题 Given a tensorflow event file, how can I extract images corresponding to a specific tag, and then save them to disk in a common format e.g. .png ? 回答1: You could extract the images like so. The output format may depend on how the image is encoded in the summary, so the resulting write to disk may need to use another format besides .png import os import scipy.misc import tensorflow as tf def save_images_from_event(fn, tag, output_dir='./'): assert(os.path.isdir(output_dir)) image_str = tf

Tensorboard Error: No dashboards are active for current data set

阅读更多关于 Tensorboard Error: No dashboards are active for current data set

问题 I am trying to use Tensorboard but every time I run any program with Tensorflow, I get an error when I go to localhost:6006 to view the Visualization Here is my code a = tf.add(1, 2,) b = tf.multiply(a, 3) with tf.Session() as sess: writer = tf.summary.FileWriter("output", sess.graph) print(sess.run(b)) writer.close() When I go to the command prompt and enter tensorboard --logdir=C:\path\to\output\folder It returns with TensorBoard 0.1.8 at http://MYCOMP:6006 (Press CTRL+C to quit) When I go

Gradients are always zero

阅读更多关于 Gradients are always zero

I have written an algorithm using tensorflow framework and faced with the problem, that tf.train.Optimizer.compute_gradients(loss) returns zero for all weights. Another problem is if I put batch size larger than about 5, tf.histogram_summary for weights throws an error that some of values are NaN. I cannot provide here a reproducible example, because my code is quite bulky and I am not so good in TF for make it shorter. I will try to paste here some fragments. Main loop: images_ph = tf.placeholder(tf.float32, shape=some_shape) labels_ph = tf.placeholder(tf.float32, shape=some_shape) output =

Accessing Tensorboard on AWS

阅读更多关于 Accessing Tensorboard on AWS

问题 I'm trying to access Tensorboard on AWS. Here is my setting : Tensorboard : tensorboard --host 0.0.0.0 --logdir=train : Starting TensorBoard b'39' on port 6006 (You can navigate to http://172.31.18.170:6006) AWS Security groups (in): HTTPS TCP 443 0.0.0.0/0 Custom_TCP TCP 6006 0.0.0.0/0 However connecting to ec2-blabla.us-west-1.compute.amazonaws.com:6006 I can't see anything, I basically can't connect. Do you have any idea? 回答1: You can use ssh tunneling technique. In your terminal you can