imagenet | Pytorch Imagenet Models Example Transfer Learning | Machine Learning library

The following source code could get both probabilities and logits from an imagenet pretrained model in Tensorflow

I am trying to implement a t-SNE visualization in tensorflow for an image classification task. What I mainly found on the net have all been implemented in Pytorch. See here.

Here is my general code for training purposes which works completely fine, just want to add t-SNE visualization to it:

I am new to hugging face and want to adopt the same Transformer architecture as done in ViT for image classification to my domain. I thus need to change the input shape and the augmentations done.

From the snippet from huggingface:

I am currently using a model from tf.keras.applications for training. And a data augmentation layer along with it. Wierdly, after I import the model from applications, the augmentation layer does not work. The augmentation layer does work before I import it. What is going on?

Also, this has only started happening recently after the new version of TF 2.8.0 was released. Before it was working all fine.

The code for the augmentation layer is

TL;DR - ML model loss, when retrained with new data, reaches NaN quickly. All of the "standard" solutions don't work.

Hello,

Recently, I (successfully) trained a CNN/dense-layered model to be able to classify spectrograms (image representations of audio.) I wanted to try training this model again with new data and made sure that it was the correct dimensions, etc.

However, for some reason, the BinaryCrossentropy loss function steadily declines until around 1.000 and suddenly becomes "NaN" within the first epoch. I have tried lowering the learning rate to 1e-8, am using ReLu throughout and sigmoid for the last layer, but nothing seems to be working. Even simplifying the network to only dense layers, this problem still happens. While I have manually normalized my data, I am pretty confident I did it right so that all of my data falls between [0, 1]. There might be a hole here, but I think that is unlikely.

I attached my code for the model architecture here:

I am a bit new at Deep learning and image classification. I want to extract features from an image using VGG16 and give them as input to my vit-keras model. Following is my code:

My code snippet is below -

I created a train set by using ImageDataGenerator and tf.data.Dataset as follows:

I built a cnn model that classifies facial moods as happy , sad, energetic and neutral faces. I used Vgg16 pre-trained model and freezed all layers. After 50 epoch of training my model's test accuracy is 0.65 validatation loss is about 0.8 .

My train data folder has 16000(4x4000) , validation data folder has 2000(4x500) and Test data folder has 4000(4x1000) rgb images.

1)What is your suggestion to increase the model accuracy?

2)I have tried to do some prediction with my model , predicted class is always same. What can cause the problem?

What I Have Tried So Far ?

1. Add dropout layer (0.5)
2. Add Dense (256, relu) before last layer
3. Shuff the train and validation datas.
4. Decrease the learning rate to 1e-5

But I could not the increase validation and test accuracy.

My Codes