Questions tagged [tensorflow]
TensorFlow is an open-source library and API designed for deep learning, written and maintained by Google. Use this tag with a language-specific tag ([python], [c++], [javascript], [r], etc.) for questions about using the API to solve machine learning problems. The programming languages that can be used with TensorFlow API vary, so you must specify the programming language. Please specify the application area such as [object-detection] as well.
tensorflow
82,916
questions
0
votes
0
answers
9
views
ValueError: Unable to create dataset (name already exists) for federated learning
Traceback (most recent call last):
File "/Users/Federated_2Clients/Retrain_2Clients.py", line 178, in <module>
Train_Model = RetrainModel(x0, y0, x1, y1)
File "/Users/...
- 1
0
votes
0
answers
17
views
I am trying to make a FastAPI for my Deep Learning model, but it does not seem to replicate the results it did when I tested it in Colab
My model is entirely made on Google Colab, I made it using Tensorflow and Keras. I tried to replicate a model which I saw as tutorial on YouTube, which I later wanted to make a website for. Thus, I ...
0
votes
0
answers
12
views
tensorflow.keras.Normalization in Google Colab Notebook
Apologies if this is a basic question. In the following python code I try to normalize a simple tensor using a Google Colab notebook.
import tensorflow as tf
import pandas as pd
from tensorflow.keras....
- 3
0
votes
1
answer
18
views
tf.keras.models.load_model fail to load a model that was saved with tf.keras.models.save_model
I'm trying to load a previously trained model but it gives me this error. Is there any way I can convert this file format to the new format or how do I fix this? I'd rather not have to train a new ...
- 15
0
votes
0
answers
15
views
ValueError: Error when checking input: expected conv2d_input to have 4 dimensions, but got array with shape (1, 1, 2)
I am working with farama gymnasium trying to make an ai to learn to play an atari game. But I am encountering this error. Here is my code:
import gymnasium as gym
import random
import numpy as np
from ...
0
votes
0
answers
63
views
What interfered with my expected OpenMP behavior in the custom operator of C++ TensorFlow 1.12?
I implemented my computation logic in C++ (actually using C++ code generated by PyTorch's Inductor), utilizing OpenMP to accelerate Tensor computations. For example, one of the functions is as follows:...
- 1
0
votes
0
answers
29
views
Epoch 1/3 ^C - model.fit() was terminated with this line and without any error
I'm developing a U_Net Model for Segmentation. My Train dataset shape is
[{'image', [32, 128, 128, 2]}; {'detection', [32, 128, 128, 2]}]
such that { 'image', [number of MRI slices, height, ...
- 11
-2
votes
1
answer
30
views
modeel = tf.keras.models.load_model('trained_model.keras')
ValueError Traceback (most recent call last)
Cell In[20], line 1
----> 1 modeel = tf.keras.models.load_model('trained_model.keras')
File c:\Users\arman\AppData\Local\...
- 1
0
votes
0
answers
22
views
Converted Model Using TensorFlow.JS Converter Not Working
I was following the TFJS WebML YT Course from Jason Mayes and following along to the TFJS Converter video, here's my notebook:
Google Colab Notebook
Basically it is an exact replica from the video and ...
0
votes
0
answers
23
views
add_hparams() function from TensorBoard doesn't work properly
I'm trying to add metrics to this SummaryWriter, but it's not working.
I'm using the add_hparams() function of SummaryWriter, the details of which can be found here: https://pytorch.org/docs/stable/...
- 3
0
votes
0
answers
11
views
tflite model load failed on Android (IsPowerOfTwo(RFFT2D fft_length_data[1]) was not true.)
to get mfcc features from android. built mfcc model with tf.
and I checked works fine.
but when I convert it to tflite and try to load it on Android, error comes while loading.
error logs.
java.lang....
- 11
0
votes
0
answers
18
views
Facing Memory Issues in Google Colab When TESTING/training TensorFlow Time-Series Model
training often crashes due to Out of Memory (OOM) errors, this seems to be a fairly novel problem after I moved some functions into classes in a utils.py script and made slight changes to the ...
0
votes
0
answers
7
views
Layer-specific learning rate (Tensorflow)
I'm trying to implement a simple DQN model with layer-specific learning rate. I'm using a sequential keras model with only two hidden and one output layer.
Unfortunately, the Tensorflow-addons package ...
- 1
0
votes
0
answers
18
views
Reshaping spatiotemporal dimension of mmap numpy so that it can be fed to ConvLSTM2D
I have this tensor of multidimensional array:
# read from memory-mapped files
# File paths for memory-mapped files
input_file_path = 'tensor_input.dat'
output_file_path = 'tensor_output.dat'
# ...
0
votes
0
answers
10
views
Tensorflowjs keras model node weights aren't recognized
I'm facing an error when calling a pre-trained keras model in javascript for a simple web app on Heroku.
https://digit-predictor-6ba58c0cd85a.herokuapp.com
Unhandled Promise Rejection: Error: ...
- 1