Questions tagged [tensorflow2.0]
Use this tag when asking about TensorFlow 2.0. You may consider using the [tag: tf.keras] tag for questions specific to that API.
tensorflow2.0
5,771
questions
0
votes
0
answers
17
views
tf.tile in sparse format in Tensorflow
How do I perform following operation in sparse implementation?
multiple = tf.constant([a,b],tf.int32)
T_tiled = tf.tile(T, multiple)
- 143
0
votes
0
answers
17
views
Tensorflow GEMM launch failures
I'm rnning a GNN model using virtual environment.My GPU is RTX 4050,
my max CUDA driver version shown on setting is 12.3
so I choose my tensorflow version 2.0.0 according to a blog with CUDA 10.0.130/...
0
votes
0
answers
9
views
Display result of overall loss validation graph
Can I display the results of the overall loss validation graph from the last checkpoint? so I can see the difference between learning curve loss train and loss vall, because from the code that I run ...
-1
votes
1
answer
34
views
'tuple' object has no attribute 'rank'
This is a FabricNet sample implementation (official code). As it was in the research paper, the input image size is 120x120x3. I tried the below code, but it throws the error 'tuple' object has no ...
0
votes
1
answer
23
views
how do link eigen3 when compiling tensorflow?
While reading tensorflow source code, I found eigen3 folder only includes #include file as below. If not exist ".cpp" or other source code, I have a question: how do link corresponding ...
- 49
0
votes
0
answers
23
views
how to set checkpoint with efficientdet model and tensorflow object detection API
I have run the training process, but for the evaluation I run only at the last checkpoint step, can someone help me to provide input so that I can change the checkpoint assignment per 100 steps, so ...
-1
votes
0
answers
37
views
Input 0 of layer "dense" is incompatible with the layer: expected axis -1 of input shape to have value 36864, but received input with shape (190,1536)
I am trying to create a model for image classification for grayscale images. and got the error:
ValueError: Exception encountered when calling Sequential.call().
Input 0 of layer "dense" is ...
0
votes
0
answers
23
views
Error when implementing SHAP on CNN model
So I am trying to implement SHAP to a CNN model I trained on an image dataset on Kaggle. But I keep getting the following Attribute Error:
--------------------------------------------------------------...
- 1
0
votes
1
answer
11
views
INVALID_ARGUMENT: You must feed a value for placeholder tensor 'conv2d_input' with dtype float and shape
I was trying to build a gradient heatmap model using the following code:
import tensorflow as tf
import tensorflow.keras.layers as klayers
import tensorflow.keras.models as kmodels
import tensorflow....
- 1
0
votes
0
answers
54
views
TensorFlow Lite Model Compatibility Issues with Feedback Manager and oneDNN Custom Operations
for the Python code given below. I am getting this error. Please, anyone, help me with this.
2024-07-15 17:11:36.038742: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may ...
- 15
0
votes
0
answers
11
views
Convert tensorflow code from old version to new version of the library
I have the following custom trainer in tensorflow code (1.14).
class CorefModel(object):
def __init__(self, config):
#some initialization...
input_props = []
input_props.append((tf....
- 1,078
0
votes
0
answers
19
views
Loading model error. How can I fix this error?
I am trying to build a rock paper scissor detection program. When I am trying to load my saved model from local directory using the load_model function from tf.keras.models I am encountering this ...
0
votes
1
answer
38
views
ImportError: cannot import name 'CuDNNLSTM' from 'tensorflow.keras.layers'
I am learning Machine Learning and AI and looking at a code written about 2-3 years back. Here is part of the code where I a facing issue:
import pandas as pd
import numpy as np
import random
import ...
- 205
0
votes
0
answers
17
views
Resolving type conversion error for Keras functional model with categorical features of different datatypes
I am working on creating a model which imports a csv of categorical string and numeric data as well as continuous features to predict if a student will graduate.
Index
Age
Household_Size
Gender
...
- 1
0
votes
0
answers
11
views
How to restart a GAN Training with TensorFlow 2.15 using checkpoints
I'm working on creating a Jupyter notebook for training a GAN using TensorFlow, and I want to be able to restore the last checkpoint to continue training from where I left off.
I am following this ...
