Extract features from pre-trained model

Hi! I fine-tuned a I3D_ResNetV1 action recognition model on a custom dataset, and obtained a model-symbol.json and a model-0000.params files. Now, I can load and use the model by:

model = mx.gluon.nn.SymbolBlock.imports(symbols_file_path, ["data"], parameters_file_path, ctx=context)

However, I don’t want to get the final output of the model, but only the output of the feature extractor. Do you know how can I do this?