All Questions
49 questions
1
vote
1
answer
130
views
I am learning tensorflow2 in python and i am wondering what sets the ndim?
def build_model(layers):
model = Sequential()
# By setting return_sequences to True we are able to stack another LSTM layer
model.add(LSTM(layers[0], input_shape=(1, 2), return_sequences=...
- 39
0
votes
1
answer
72
views
Accuracy falling down tensorflow v1.5
I'm using tensorflow 1.5 and keras 2.1.6. The code is taken from this tutorial and reworked to work on version 1.5. There is it:
import tensorflow as tf
import keras
import numpy as np
import ...
- 43
0
votes
1
answer
1k
views
ModuleNotFoundError: No module named 'tensorflow.compat' in tensorflow1.4 and python3.6 and cuda 8.0
I am trying to run a DL code based.
My set up is :
tensorflow 1.4
python 3.6
cuda 8.0
I am getting all the time the same error :
Traceback (most recent call last):
File "demo.py", line 285,...
- 141
1
vote
0
answers
129
views
Tensorflow 2.1 gives different neural net convergence on windows vs linux for Python 3.6
Machine 1 :
LAMBDA QUAD LINUX Ubuntu:18.04
Deep Learning Workstation with 4 GPUs
convergence of neural net model on lambda ( Linux)
Machine 2 :
Lenovo Thinkpad T480 Intel Windows 10.
convergence of ...
- 11
2
votes
1
answer
4k
views
can't import tensorflow in python, windows 10 64 bit
I am trying to make a AI chatbot using python. This requires tensorflow. I installed it using pip and when I try to import it, it isn't working. I got this Traceback:
Installation
C:\Users\vross>...
user12841218
2
votes
1
answer
1k
views
Running a SavedModel in TensorFlow 2 with inputs of a specific type
I'm trying to run an object detection model I have prepared in SavedModel format in TensorFlow 2.
The model takes inputs in the format of a byte-encoded JPEG, PNG, or GIF as ...
- 110
0
votes
0
answers
500
views
Trouble Installing Tensorflow - Building wheel for wrapt (setup.py) ... error
Whenever I try to install tensorflow I keep getting the following error message. Is there an easy fix for problem?
(py3.6) C:\Users\matthew>pip install tensorflow --no-cache-dir
Collecting ...
- 31
0
votes
1
answer
835
views
What's a compatible GLIBC version for tensorflow 2.0 for python3.6.8 on CentOS 6.9?
The server currently has CentOS 6.9 with GLIBC 2.12 and tensorflow 1.14.
tensorflow is throwing error saying that it needs GLIBC 2.15.
Now I want to upgrade tensorflow to 2.0 but I want to know what'...
- 9,028
2
votes
2
answers
3k
views
How to use OpenMP parallelism effectively with tensorflow 1.14.0
I'm currently trying to find an effective way of running a machine learning task over a set amount of cores using tensorflow. From the information I found there were two main approaches to doing this.
...
0
votes
1
answer
752
views
AttributeError: 'module' object has no attribute 'app' : TensorFlow Image Classifier
I am trying to train a new model, based on my custom dataset of images, so it can be my personalized image classifier.
I strictly followed the tutorial from this link: "https://medium.com/@teavanist/...
1
vote
0
answers
686
views
Tensorflow ImportError: DLL load failed: The specified module could not be found
I've seen that a lot of questions have already asked this, but it seems to be very specific as none of the answers seem to work.
Let me explain the steps that I have taken to install everything:
I ...
- 1,981
10
votes
3
answers
1k
views
Issue with embedding layer when serving a Tensorflow/Keras model with TF 2.0
I followed the step in one of the TF beginner tutorial to create a simple classification model. They are the following:
from __future__ import absolute_import, division, print_function, ...
- 12.4k
2
votes
1
answer
4k
views
ImportError: TensorBoard
I'm using Python in Anaconda environment (jupyter notebook)
OS: Ubuntu
Tensorflow version: 1.14.0
Python version: 3.6
https://github.com/tensorflow/tensorboard/issues/1425
This is the same issue,...
- 827
2
votes
2
answers
2k
views
Upgrading from tensorflow 1.x to 2.0
I am new to tensorflow.
Have tried this simple example:
import tensorflow as tf
sess = tf.Session()
x = tf.placeholder(tf.float32)
y = tf.placeholder(tf.float32)
z = x + y
print(sess.run(z, feed_dict=...
- 2,107
3
votes
2
answers
8k
views
ValueError: total size of new array must be unchanged (Reshape from keras)
For this toy model:
from keras.layers import Input, Dense, Reshape
from keras.models import Model
# this is the size of our encoded representations
compression = 10
input_img = Input(shape=(28,28,...
- 5,474