Questions tagged [sess.run]
8 questions
4
votes
1 answer
sess.run() is too slow
The sess.run() function by the Tensorflow object detection module takes about 2.5 seconds to detect bounding bozes in a 600x600 image. How can I speed up this code?
def run(image, detection_graph):
with detection_graph.as_default():
with…
SKAE
- 83
- 1
- 10
1
vote
0 answers
Can I run 2 sessions in parallel using Tensorflow V1? Is it correct to write the programming in the following manner?
I would like to optimise 2 optimisers/ functions using the tensorflow v1 using the training set, hence would like to run the 2 optimisers in parallel.
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
# ...
loss_i1 = -…
Dione Goh
- 11
- 1
1
vote
1 answer
Issue with feeding value into placeholder tensor for sess.run()
I want to get the value of an intermediate tensor in a convolutional neural network for a specific input. I know how to do this in keras and even though I have trained a model using keras, I'm going to move towards constructing and training the…
Jane Sully
- 3,137
- 10
- 48
- 87
1
vote
0 answers
Sess.run with string variable name
I have been studying the book "Tensor flow for Dummies" and there is a piece of code to restore variables earlier stored
with tf.Session() as sess:
# Load stored graph into current graph
saver = tf.train.import_meta_graph('output.meta')
# Restore…
Priyank Jain
- 11
- 1
0
votes
0 answers
Training with a loss function consisting of two part based on two different dataset
The loss function is defined as shown in the link
The training is based on two different dataset i and k, which corresponds to the two different parts of the loss function.
I would like to train using
for epoch in range(training_epochs):
…
0
votes
1 answer
Speeding up Inference time on GPT2 - optimizing tf.sess.run()
I am trying to optimize the inference time on GPT2. The current time to generate a sample after calling the script is 55 secs on Google Colab. I put in timestamps to try to isolate where the bottleneck is.
This is the code:
for _ in range(nsamples…
0
votes
1 answer
TensorFlow RNN example from book (word2vec, embeddings, )
Guided by the book with name "Learning TensorFlow. A Guide to Building Deep Learning Systems (Tom Hope, Yehezkel S. Reshe , and Itay Lieder)" I'm trying to implement simple RNN network with word2vec approach.
On page 101 (Chapter 6, Text II: Word…
DustyDust
- 5
- 3
0
votes
0 answers
Training Mini-batches of data (without labels) for unsupervised learning
Has anyone trained mini-batches of data for an unsupervised learning problem?
The feed_dict uses the label and in an unsupervised setting. How do you overcome that? Could we use fake labels that never contribute to the loss function?
Basically, I…
Vishal
- 227
- 1
- 2
- 8