723 questions
0
votes
0
answers
63
views
How can AUC be correctly used with a softmax output, sparse integer labels and categorical_crossentropy for binary classification in Keras?
I am working on a binary image classification task using TensorFlow/Keras (TensorFlow version: 2.19.0). My model architecture is a multimodal setup with two input branches (CT and PET scans), and its ...
Advice
1
vote
0
replies
45
views
Transfer Learning: How do I only save the parameter I trained to save disk space?
So, I am having a transfer learning project using VGG16, however as we all know its model size is over 500MB. I somply don't have enough disk space to save more than 200 instance of said model, ...
- 11
1
vote
1
answer
535
views
Transfer learning insightface on my own dataset
I'm currently working on transfer learning with InsightFace using the glint360k_cosface_r100_fp16_0.1 model from the ArcFace Torch section. However, I'm facing issues with either overfitting or ...
- 11
1
vote
0
answers
40
views
CNN Model learning improperly returning extrema values
I've been working on a binary object detection CNN model using transfer learning with keras' built in resnet 50 model. However after multiple times of training over 100 epochs it is returning ...
- 11
0
votes
1
answer
56
views
What should be my classifier in Transfer Learning using MaxViT?
I am trying to do transfer learning on Pytorch pretrained models with custom dataset. I have been able to successfully perform transfer learning with SqueezeNet.
For Squeezenet my classifier was, ...
- 5
0
votes
1
answer
87
views
How to manage memory consumption in deep learning models?
When I run this code, the runtime session automatically closes. There is no space in RAM left. Hence the session closes automatically. I am using pytorch in Google Colab notebook. I tried switching ...
1
vote
0
answers
63
views
Implementing Transfer Learning to train a CNN Model for Distracted Driver Detection
I want to use EfficientNetB0 (or any other base models) from tensorflow.keras.applications to detect distracted drivers. The given dataset consists of approximately 22.5k training images, roughly ...
- 11
1
vote
0
answers
29
views
Asynchronous parallel data loading with torch in R
I want train cnns on a big dataset via transfer learning using torch in R. Since my dataset is to big to be loaded all at once, I have to load each sample from the SSD in the dataloader. But loading ...
- 11
-1
votes
1
answer
281
views
Transfer Learning in EfficientNet for Binary Classification Task stuck at 50%
I've been trying to do transfer learning in EfficientNet in a binary classification task.
My directory structure looks like this:
training
├── label0
└── label1
validation
├── label0
└── label1
and ...
-2
votes
1
answer
38
views
About tensorflow_hub
hi guys i'm successfully import tensorflow_hub.
but when I trey to run this code part
"
**IMAGE_SHAPE = (224, 224)
classifier = tf.keras.Sequential([
hub.KerasLayer(classifier_model, input_shape=...
2
votes
0
answers
393
views
Layer count mismatch when loading weights from file transfer learning in keras
I'm new to convolutional neural network and machine learning in general, so sorry in advance if my question is really straighforward, but I have searched for a while without getting a solution to fix ...
- 21
0
votes
0
answers
50
views
save tensorflow model using transfer learning
I am trying to save a model which uses transfer_learning but I'm unable to make it work once I reconstruct it. This is my code:
import numpy as np
import tensorflow as tf
import tensorflow_hub as hub
...
0
votes
1
answer
198
views
ValueError: The layer sequential has never been called and thus has no defined input. on transfer learning
I am working on network_based transfer learning with iris dataset.
it shows a error：
ValueError: The layer sequential has never been called and thus has no defined input.
on the line
...
- 1
0
votes
1
answer
130
views
How to save model and load model in ReactJS
im follwing the transfer learning course of tensorflowjs on youtube. Im trying to make a model recognize some picture i upload. The problem is when i close window or reload, the model is load from ...
-1
votes
2
answers
149
views
Transfer Learning: Image classification High accuracy but very high val_loss. Why?
I'm using tensorflow and Keras to do transfer learning using Resnet_50. The issue I am having is that my model seems to be doing good on accuracy but my val_loss is extremely high as well as when i ...
- 37