How a Convolutional Neural Net handles channels
I've looked through a lot of explanations of the way a CNN conventionally handles multiple channels (such as 3 in an RGB image) and am still at a loss.
When a 5x5x3 filter (say) is applied to a patch of an RGB image what exactly happens? Is it in fact 3 different 2D convolutions (with independent weights) that happen separately to each channel? And then the results get simply added together to produce the final output to pass to the next layer? Or is it a truly 3D convolution?
This image is from Andrew Ng's deeplearning.ai course. 6 X 6 X 3 - where 3 corresponds to 3 color channels. 6 X 6 being the height and widht of the image. For the convolution step we convolve the input image with 3 X 3 X 3 filter/kernel. The input image and filter both will have 3 layers. (Mostly both are same for input image and filter).The output will be 4 X 4 X 1. 3 X 3 X 3 gives you 27 features/parameters which you multiply with the corresponding Red, Green and blue channels. Finally add up all those numbers to get the value for [0,0] in 4 X 4 output image. Now move the yellow cube of the input image and slide it over 1 box to your right and once it reaches the right end, you slide the cube one row down and continue your multiplication to fill the 4 X 4 output. Would suggest you to take a paper and pencil, fill random values in all the cubes for input as well as the kernel and solve the multiplication.
For more details watch these lectures on youtube. https://www.youtube.com/watch?v=KTB_OFoAQcc&index=6&list=PLkDaE6sCZn6Gl29AoE31iwdVwSG-KnDzF
- How to fix the learning-rate for Huggingface´s Trainer?
- Roboflow Vs. Darknet for generating weight file and creating the model
- What is the difference between backpropagation and reverse-mode autodiff?
- Load Registered Component in Azure ML for Pipeline using Python sdk v2
- classifiers in scikit-learn that handle nan/null
- Encoding two categorial data present in same dataset in Deep learning
- Machine learning in q/kdb+
- Why do the sensitivity (recall) values differ between classification_report and precision_recall_fscore_support in a loop?
- How do you specify the bfloat16 mixed precision with the Intel Extension for PyTorch?
- mlflow doesn't autolog artifacts while logging images
- Choosing top k models using GridSearchCV in scikit-learn
- Calculating pairwise distances between entries in a `torch.tensor`
- Reusing a feature to split regression decision tree's nodes
- Fine tuning LayoutLmv3 using Cord-V2 dataset
- What does model.eval() do in pytorch?
- ElasticNetCV in Python: Get full grid of hyperparameters with corresponding MSE?
- Why is the accuracy for my Keras model always 0 when training?
- Polars - issues with performance - attempting to create a new dataframe per row
- Keras model.export() fails because of NoneType shapes in model
- Meta-feature analysis: split data for computation on available memory
- Single-headed transformer model, output and target tensor sizes don't match
- How to add the bounding box values to the labels text files during prediction with a trained YOLO-V8 instance segmentation model?
- How to calculate correlation of colours in a dataset?
- Convert array of indices to one-hot encoded array in NumPy
- Import custom prediction routine to vertex AI pipeline
- what is the difference between bigram and unigram text features extraction
- How to map the results of Principal Component Analysis back to the actual features that were fed into the model?
- How to calculate optimal batch size?
- Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample
- Center an image and adding a background at export