It is straightforward just by looking at the figure below that this dataset is highly unbalanced, having a lot of samples only for two classes i.e. ''capacitor'' and ''resistor''. In this situation, it is not a good idea to use this dataset as it is, simply because the models will be trained on image batches mainly composed by of the most common components, hence learning only a restricted number of features. This has as a consequence that the models will probably be very good at classifying ''capacitor'' and ''resistor'' classes and pretty bad at classifying the remaining ones. Therefore, the missing data must be increased with image augmentation.

Before proceeding further, please note that the number of DSLR subset examples is by far lower than the number of the Microscope subset samples. As the two subsets were acquired using two different kind kinds of instruments, their characteristics — the resolution, for example — differ significantly. In order to have homogeneous images w.r.t. the characteristics, it is preferable to keep only one of them, specifically the most numerous.

==Training configuration and hyperparameters setup==All the models were trained with the same configuration, using 1000 epochs with 20 steps per epoch for both training and validation, with a reduced batch size of 32 images, learn rate set at {{val|1e-5}}, and dropout rate set at {{val|1e-5}}. Patience for early stopping was set at 100 epochs.