Questions tagged [gradienttape]
147 questions
0
votes
1 answer
Avoid Warnings during Jacobian Matrix Calculation
I have a trained LSTM model. I would like to calculate the Jacobian matrix of the output w.r.t input. I have written the following code:
data = pd.read_excel('filename')
a = data[:20] #shape is (20,5)
b = data[50:70] #shape is (20,5)
A =…
Pradyumna
- 13
- 4
0
votes
3 answers
Using Gradient Tape for Jacobian of LSTM model - Python
I am building a sequence to one model prediction using LSTM. My data has 4 input variables and 1 output variable which needs to be predicted. The data is a time series data. The total length of the data is 38265 (total number of timesteps). The…
Pradyumna TK
- 143
- 1
- 8
0
votes
1 answer
Problem about getting None from the GradientTape.gradient in TensorFlow
I tried the following code:
from d2l import tensorflow as d2l
import tensorflow as tf
@tf.function
def corr2d(X, k, Y): #@save
"""Compute 2D cross-correlation."""
with tf.GradientTape() as tape:
for i in range(Y.shape[0]):
…
C Chiang
- 1
0
votes
1 answer
Checking condition in call method of custom layer using tf.cond()
I'm implementing a custom layer in tensorflow 2.x . My requirement is such that, the program should check a condition before returning the output.
class SimpleRNN_cell(tf.keras.layers.Layer):
def __init__(self, M1, M2, fi=tf.nn.tanh,…
Lawhatre
- 1,302
- 2
- 10
- 28
0
votes
1 answer
Is it possible to acquire an intermediate gradient? (Tensorflow)
When using gradient tape you can calculate the gradient after using:
with tf.GradientTape() as tape:
out = model(x, training=True)
out = tf.reshape(out, (num_img, 1, 10)) # Resizing
loss =…
user13906837
0
votes
1 answer
How do I access Tensor values (e.g. Metrics) which are updated within a tf.function?
I have been working on a model whose training loop uses a tf.function wrapper (I get OOM errors when running eagerly), and training seems to be running fine. However, I am not able to access the tensor values returned by my custom training function…
sbab94
- 1
0
votes
1 answer
Tensorflow gradient always gives None when using GradientTape
I was playing around and trying to implement my own loss function in TensorFlow but I always get None gradients. To reproduce the problem I've now reduced my program to a minimal example. I define a very simple model:
import tensorflow as tf
model…
man zet
- 826
- 9
- 26
0
votes
1 answer
GradientTape not computing gradient
I understand that so long as i am defining a computation in tf.GradientTape() context, the gradient tape would compute the gradient w.r.t all the variables that the output of the computation depends on. However, i think i am not quite grasping the…
figs_and_nuts
- 4,870
- 2
- 31
- 56
0
votes
0 answers
Gradient Calculation in Tensorflow using GradientTape - Getting unexpected None value
I am having a problem calculating the gradient in TensorFlow 1.15. I think it's something related context manager or keras session, but I am not sure about it. Following is the code I have written:
def create_adversarial_pattern_CW(input_patch,…
Tarun Gupta
- 19
- 5
0
votes
1 answer
Jacobian matrix of logits with respect to image using tf.GradientTape
I am trying to find the Jacobian of logits with respect to input but I do get None and I could not figure it why.
Let'say I have a model, I trained it and saved it.
import tensorflow as tf
print("TensorFlow version: ",…
ARAT
- 884
- 1
- 14
- 35
0
votes
3 answers
How to save and load model with tf.gradienttape in tenworflow2
I am using tf.gradienttape for model training and it is successful to save checkpoints for every epoch.
with train_summary_writer.as_default():
with tf.summary.record_if(True):
for epoch in range(epochs):
for train_id in…
Brian Lee
- 173
- 3
- 14
0
votes
1 answer
Error when working with GradientTape() and jacobian() in Tensorflow 2.0
I am working with GradientTape() and jacobian() in Tensorflow 2.0 in Python.
This code executes fine:
x = tf.Variable(2.0, dtype=tf.float32)
with tf.GradientTape() as gT:
gT.watch(x)
g = tf.convert_to_tensor([x, 0.0], dtype=tf.float32)
dg =…
Kalia
- 29
- 1
- 6