CODEWITHSUNDEEP
pythontensorflowtime-complexityspace-complexity
Joseph Budin
Joseph Budin

Reputation: 1360

What is the complexity of strided slice in Tensorflow?

I am wondering what is the complexity of the strided slice function in Tensorflow. Obviously, it is not as computationally intensive as a Convolution 2D, but it's certainly not free neither. I'm not even sure talking of complexity for this operation is meaningful since there is no addition or multiplication performed. To be concrete, let's say I have a 10x3x3x10 tensor foo and I want to perform bar=foo[3:5,:,:,4:5]. How would you evaluate the complexity of the operation (both in terms of space and time)?

Upvotes: 3

Views: 270

Answers (1)

user11530462
user11530462

Reputation:

You can use TF_Strided_Slice Operation and Conv2D Operation and then evaluate the complexity of those Operations using Profiling in Keras Callback.

Corresponding code is mentioned below:

log_dir="logs/profile/" + datetime.now().strftime("%Y%m%d-%H%M%S")

tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1, profile_batch = 3)

model.fit(train_data,
          steps_per_epoch=20,
          epochs=5, 
          callbacks=[tensorboard_callback])

Upvotes: 2

Related Questions