'changing a trained static input shape to dynamic shape in keras

I have trained my MobileNetV3Small with 2 dense layers and got my result. but I set 640,480,3 as my input shape and now I need to test some images with different sizes. as it starts with convolution layers size must not matter. but I received errors as it requires its defined size (640,480,3) and padding and resizing didn't perform well. so I want to change the input shape to (None, None,3) without retraining it from scratch. It took 3 days to train my model and I don't want to train it again to change the input size.

tensorflowkerasdeep-learningneural-network


Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source

Related Questions

Create custom convolution layer and compare two keras layers

Neural Network Always Produces Same/Similar Outputs for Any Input [closed]

Are modern CNN (convolutional neural network) as DetectNet rotate invariant?

Extract weights and biases from Orange Data Mining

How are SHAP's feature contributions calculated for models with word embeddings as output?

What is "linear projection" in convolutional neural network [closed]

Error while defining observation space in gym custom environment

training = False in Keras Sequential API

Ordering of batch normalization and dropout?

ran into TensorFlow ValueError during my TensorFlow Course with Udemy

AssertionError: Wrong values for d['w'] | deeplearning specialization

Dependent hyperparameters with keras tuner

Why do we need to call zero_grad() in PyTorch?

Why do we need to call zero_grad() in PyTorch?

What is the time-complexity of the pseudo-inverse in pytorch (i.e. torch.pinverse)?