Questions tagged [image-classification]
579 questions
-2
votes
1 answer
Why does my model perform good on test dataset but very bad on real data?
I am writing a character recognizing CNN. I have used
EMNIST Dataset.
Kaggle Notebook link : https://www.kaggle.com/code/notshrirang/ocr-with-cnn
GitHub Notebook link : https://github.com/NotShrirang/MyOCR
My model does pretty good on testing…
Shrirang Mahajan
- 88
- 9
-2
votes
2 answers
Is my CNN model still overfitting? If so, how can I combat it? Is there something wrong with my architecture?
My CNN model kept getting high accuracy/low loss during training and much lower accuracy/higher loss during validation, therefore I started suspecting that it's overfitting.
I have therefore introduced a few dropout layers as well as some image…
sobek17
- 1
-2
votes
1 answer
Pretrained alexnet in tensorflow
I want to use pretrained Alexnet for transfer learning. I dont see its available in Keras library.
Am I missing something here?
Other Alternative I see here is to create model and
load pretrained weight
train from scratch
Training from scratch…
Mano
- 49
- 6
-2
votes
1 answer
how to detect not in trained-for-category images when using resnet50
I have trained resnet50 on four categories of images. It works fantastic when I feed it an image in any one of the four categories -- I have essentially 100% accuracy on images in these categories.
However, when I feed my trained Resnet50 model an…
marlon1492
- 21
- 5
-2
votes
1 answer
How can I increase my validation accuracy?
I am working on a word-based sign language recognition system. I'm new to deep learning. My experience is limited. I have 10 classes. The size of the data ( 1256, 32, 112, 112, 3). For video classification I use 3D CNN, which has been mentioned in…
-2
votes
1 answer
Image classification Using Pytorch
this is the code where I was working on Image Classification using Pytorch and I'm not able to get the accuracy right.
the accuracy is exceeding 100 ,can anyone help me to find the error.
def trained_model(criterion, optimizer, epochs=5):
…
-2
votes
1 answer
Expecting a Binary value but predicts a float number
I created a neural network which takes images of people as X_training values and their respective genders (binary value) as the Y_train values, where my goal is to predict the relevant gender once a user enters a image. Here is the code where i set…
Yeshan Santhush
- 87
- 7
-3
votes
1 answer
Multi-label classification return more than 1 class in each label
How to train a Multi-label classification model when each label should return more than 1 class?
Example:
Image classification have 2 label: style with 4 classes and layout with 5 classes.
An image in list should return 2 style and 3 layout like [1…
Tùng Dương Quang
- 57
- 5
-4
votes
2 answers
Image classification Using CNN
I am working on breast cancer classification. I found this online code to train my pre-processed outputs on it. The results was awful but I didn't understand the code, I want to train my own model but I don't how to replace my own code with this…
Eda
- 565
- 1
- 7
- 18