42,485
questions
0
votes
0
answers
6
views
Keras Graph execution error: only one input size may be -1, not both 0 and 1
I'm trying to recreate and train a 3D CNN model from a study for video action recognition and I've moved the code to Google Colab so I can run it faster because on my system is a bit slow.
But when I ...
0
votes
0
answers
52
views
The code in python and R with keras3 are different, i don't understand? [closed]
I try to convert this code write in python format to R format but the result are different and i don't understand why ?
With python :
# ---- About dataset
#
max_t = 1000
delta_t = 0.01
...
0
votes
0
answers
6
views
Invalid argument: required broadcastable shapes at loc(unknown)
I am new to DL and trying to develop an encoder-decoder with attention. When I train, it will stop just before the end of the first epoch, I guess the problem happens when the loss function tries to ...
-1
votes
1
answer
34
views
Multiclass classifier using Keras from 'Deep Learning with Python' yields very different accuracy compared to what's in the textbook
Below is the code for multi class classifier from Chapter 4 in 'Deep Learning with Python' by François Chollet. The textbook mentions this code will yield >95% training accuracy, but my environment ...
- 89
-2
votes
0
answers
13
views
When I use Jupyter Notebook to load a model, an error occurs with the function keras.saving.load_model
[Error as shown in the figure，The function is standardized, but there are many errors reported，I guess it's a configuration issue. Please advise me, big shot,I need you help]
(https://i.sstatic.net/...
0
votes
1
answer
30
views
Error in prediction step after imported a keras model to tensorflow java
my goal is to use a Keras model in a java program.
I export the keras model with model.export() and not model.save() so I get well a folder with the model in .pb format.
Then I used py .\...
- 13
-1
votes
0
answers
52
views
How to loop through generator efficiently? [closed]
Im trying to build a dataset for an OCR task following this tutorial
Im trying to loop through the generator and save the yielded images and bounding boxes to create the dataset.
i think i'm ...
0
votes
0
answers
15
views
Generate a diagram representing a complex neural network with neurons and connections in Keras?
I'm starting my studies in Neural Networks and I learn better by visualizing things.
I've created a simple neural sequential model using keras Sequential function:
model = Sequential([
Dense(units ...
0
votes
0
answers
27
views
Value Error : Sequential model 'sequential_3' has no defined input shape yet
What are common mistakes or omissions that cause the '`Sequential model has no defined input shape1 error?
Do preprocessing layers (like resize_and_rescale or data_augmentation) impact the input_shape ...
0
votes
1
answer
26
views
converting keras model to tensorflow lite to use in Kivy app
I am trying to convert the keras model to tensorflow lite, and use it in the android app development using kivy
model -
model_v3 = tf.keras.applications.MobileNet(
weights='imagenet', include_top=...
- 171
0
votes
0
answers
23
views
TqdmCallback writes loss as loss=tf.Tensor(, shape=(), dtype=float32)
I have written a VAE model in Keras following this example.
The code is working as expected, however, the loss is being printed as
loss=tf.Tensor(, shape=(), dtype=float32). As seen in the picture.
...
- 1,114
-1
votes
0
answers
23
views
Unused Tensor Affects Training in TensorFlow Model
I'm observing a difference in training loss when an unused tensor is present in my TensorFlow 2.11 model. Below is a simplified version of the code to illustrate:
import os
import random
import numpy ...
- 57
0
votes
0
answers
27
views
Invalid Argument Error in Tensorflow (Keras)
I was trying to run a deep learning project related to lip reading based on this Youtube video.
The entire code is on github.
The developer used the following versions of modules:
opencv-python -4.0....
- 11
0
votes
0
answers
23
views
How do I use "concatenate" in a Keras model without getting shape related error?
I'm trying to create a U-Net architecture in Keras 2.15. The issue arises when I introduce the "concatenate" layers. The error seems to be related to the tensor shape being passed through ...
- 1
-2
votes
1
answer
39
views
Model Always Classifies Images as Cats with High Confidence Despite Hyperparameter Tuning [closed]
I am trying to train a model on images using the code below. My directory structure is as follows:
The PetImages folder, which is approximately 1GB in size, is located next to my main.py script.
...
