All Questions
Tagged with tf.keras computer-vision
17
questions
9
votes
1
answer
7k
views
How does Tensorflow calculate the accuracy of model?
I am following this tutorial for binary class classification. While defining the model it is defined as follows and quotes:
Apply a tf.keras.layers.Dense layer to convert these features into a ...
- 570
5
votes
1
answer
6k
views
Effects of channel_shift_range in ImageDataGenerator (Keras image augmentation)
Maybe I'm misunderstanding. If I implement channel_shift_range in my ImageDataGenerator, the output should have "scrambled" color values, right? I would like to use it to make my model more robust ...
- 185
1
vote
1
answer
688
views
Tensorflow 2: How to fit a subclassed model that returns multiple values in the call method?
I built the following model via Model Subclassing in TensorFlow 2:
from tensorflow.keras import Model, Input
from tensorflow.keras.applications import DenseNet201
from tensorflow.keras.applications....
- 622
1
vote
1
answer
92
views
How do i find a solution for a prediction error
I have trained a model for Rock Paper Scissor hand gesture recognizing.
When I tried to predict using model it gives a value error.
I really confused trying to find a solution and I didnt.
Hope ...
1
vote
0
answers
369
views
Conv2DCustomBackpropInput: Size of out_backprop doesn't match computed:
The error is:
InvalidArgumentError: Conv2DCustomBackpropInput: Size of out_backprop doesn't match computed: actual = 16, computed = 5 spatial_dim: 1 input: 10 filter: 2 output: 16 stride: 2 dilation: ...
- 11
1
vote
0
answers
113
views
Computing gradients for outputs taken from intermediate layers and updating weights using optimizer
I am trying to implement below architecture and not sure in applying gradient tape properly.
In the above architecture we can see, outputs taken from multiple layers in the blue boxes. Each blue box ...
- 61
0
votes
0
answers
928
views
tensorflow/core/util/port.cc:113] oneDNN custom operations are on. The name tf.losses.sparse_softmax_cross_entropy is deprecated
I am working on a face recognition desktop application. I am using face recognition library (https://pypi.org/project/face-recognition/) and deepface (https://pypi.org/project/deepface/). I am using a ...
0
votes
2
answers
186
views
Efficient way to preprocess data for DETR model (object detection)
import keras_core as keras # so that i can use keras_cv
import keras_cv
from keras_cv import bounding_box
from keras_cv import visualization
import tensorflow as tf
import tensorflow_datasets as tfds
...
- 49
0
votes
0
answers
144
views
Creating a custom dataset in TensorFlow for training RetinaNet on image and XML annotation data
I'm currently working on training a RetinaNet model using TensorFlow and the Keras implementation provided in the official documentation (https://keras.io/examples/vision/retinanet/).However, I'm ...
0
votes
0
answers
66
views
image binary classification using Transfer learning (Dense layers with 1 or 2 Node)
I want to make a prediction with 2 classes, image binary classification.
I want to use MobileNet (transfer learning) as my algorithm, to compare trainable = True or False.
My questions are :
I tried ...
0
votes
1
answer
644
views
How to merge 2 trained model in keras?
Good evening everyone,
I have 5 classes and each one has 2000 images, I built 2 Models with different model names and that's my model code
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(32, (3, ...
- 155
0
votes
2
answers
419
views
Recent Google Colab issue after upgrade to tensorflow 2.7 in colab
When I trained my deep Learning model on Google Colab on Nov 4th 2021, I had no issues, The model was trained in half an hour using GPU instance and then default Tensorflow on Google Colab was 2.6. ...
- 1
0
votes
1
answer
60
views
Special loss function for perspective images
I am currently working on a project to detect the trackbed of railroads. The images to segemt always have the same camera perspective.
Is there a special loss function that can be used for perspective ...
- 1
0
votes
1
answer
333
views
Why save_to_dir dont work in flow_from_directory In Keras
Here i want to save the augmented pictures to a directory.but that didn't happend using the below code.I am beginner .Please Help.Thanks in advance.
import tensorflow as tf
import matplotlib.pyplot ...
0
votes
0
answers
133
views
Significant difference in performance for model.fit() when using the same training dataset in validation data
I am currently working on a simple classification problem using a feature extractor and classifier. For the feature extractor, I am using the pretrained ResNet50 model found in tf.keras.application in ...
- 1
-1
votes
2
answers
129
views
TensorFlow Binary Classification
I'm trying to make a simple binary image classification with TensorFlow, but the results are just all over the place.
The classifier is supposed to check whether my gate is open or closed. I already ...
- 334
-3
votes
1
answer
140
views
How to increase Emotion Detection Validation Accuracy on VGG16 model ? [Transfer Learning]
import pandas as pd
import numpy as np
import keras
import tensorflow
from keras.models import Model
from keras.layers import Dense
from keras import optimizers
from keras.preprocessing.image import ...
