2
Disclaimer: I will try to answer the question but promote Image Augmentation Library Albumentations, which may collaborators and I develop in free time and which we believe is the best image augmentation library at the market :)
There are many ways to augment the image data.
Spatial transforms: Crops, Flips, Transpose, Elastic transform, ShiftScaleRotate, ...
2
If you are planing to train a model which is using images taken by a single camera, I encourage you to take a look at this paper. They use a camera to track a person and recognize gestures involving arm motion. In this paper, two alternative methods for gesture recognition are compared: a template based approach and a neural network approach.
However, ...
2
I have the following suggestions.
Make sure your preprocess function in predict.py is doing exactly what datagen is doing during training (featurewise_center and normalization)
For Sigmoid value greater than 0.5 is defined as class 1 and value less than or equal is defined as class 0. In your code, for values exactly same as 0.5 are being assigned in class ...
1
as your data is very less, you should go for transfer learning as @muneeb already suggested, because that will already come with most learned parameters and then you can train that model using your custom dataset.
you can try out pre-trained models from here
If you want to go for your existing custom configured model only, try adding another Dense layer ...
1
I guess your model is biased toward the first half. Although Keras has built in shuffle=True in model.fit() arguments, according to this document it might be non-effective when steps_per_epoch=None.
I suggest shuffling your data before training using numpy.random.shuffle(array). Probably something like this:
data = np.array(data)
labels = np.array(labels)...
Only top voted, non community-wiki answers of a minimum length are eligible
