Failure to use ml5.js image classification model-Error: Based on the provided shape, [1,64,64,4], the tensor should have 16384 values but has 20155392
I trained an image classification neural network model written in ml5.js. When I try to use the model files in a p5.js web editor, I get an error 'Based on the provided shape, [1,64,64,4], the tensor should have 16384 values but has 20155392'.
The code is in this p5 sketch - https://editor.p5js.org/konstantina1/sketches/85Ny1SC2J (clicking on the arrow in the top right corner will show the files).
When I run a local server on a web page with the same structure, I see 'model ready!' (a confirmation that the model has loaded) and that's it.
I read a lot of comments that the bin file may be corrupt - I saved the model myself producing the bin file so it should be ok.
As suggested here by the author of very similar code, https://www.youtube.com/watch?v=3MqJzMvHE3E, adding pixelDensity(1) in setup() doesn't help.
I am new to machine learning, could someone please help? Thank you in advance.
The model was trained with images 64x64 px so the input test image must be the same size.
1944 (original image width) * 2592 (original image height) * 4 (number of channels) = 20155392. The tensor should have 64 (image width) * 64 (image height) * 4 (number of channels) = 16387 values. This is what the error refers to.
The copy() method used originally didn't resize the input image properly.
The correct way to resize the image is inputImage.resize(IMAGE_WIDTH, IMAGE_HEIGHT).
Working sketch: https://editor.p5js.org/konstantina1/sketches/85Ny1SC2J
- Activation functions: Softmax vs Sigmoid
- PyTorch model input shape
- Load several Images without label in keras cnn
- FastAI KeyError: "Label '755' was not included in the training dataset"
- Difficulty with stacking MNIST and Fashion_MNIST
- How to apply padding to only one side in a PyTorch Conv1d Layer?
- Dimensions in convolutional neural network
- Is there any difference between Conv1d(in, out, kernel_size=1) and Conv2d(in, out, kernel_size=1)?
- Snapdragon neural processing- SNPE
- When to use / not use bias term in convolutional neural networks
- How to verify CuDNN installation?
- What is the official implementation of first order MAML using the higher PyTorch library?
- Input type (double) and bias type (float) should be the same
- What's the correct way of expressing Residual Block with forward function of pytorch?
- ValueError: Data cardinality is ambiguous. Make sure all arrays contain the same number of samples.'x' sizes: 8 'y' sizes: 3
- How to make CNN invariant to position of a pattern in DNA sequence?
- How can I increase the accuracy of 1D CNN to estimate stress concentration factors
- Gender detection and age classification using deep learning
- Identify pixels occupied by red particles in image
- Input shape error when updating pretrained CNN from binary classification to multiclassification
- Monte Carlo (MC) dropout in Keras with R
- What am I doing wrong with my CNN that it is gaining accuracy so slowly
- RuntimeError: expected scalar type Double but found Float
- LeNet5 & Self-Organizing Maps - RuntimeError: Trying to backward through the graph a second time - PyTorch
- Pytorch CNN input dimensions not matching
- TensorFlow - ValueError: Shapes (None, 1) and (None, 10) are incompatible
- Implement max/mean pooling(with stride) with numpy
- How to overwrite nn.conv2d
- Using tensorflow, how to operate on top_k and then create a new tensor with original tensor and modified top_k
- How to load CNN saved model that have (None) input shape