genbing99/mean_spot-then-recognize

A Micro-Expression Analysis Network (MEAN) to spot-then-recognize micro-expressions

mean_spot-then-recognize's Issues

How do I recognize microexpressions use my own test examples?

Dear author, it is my great honor to star your project. I would like to ask you how to use your project to recognize micro-expressions in videos or pictures

Recognition without Spotting

can you help me to run special training on micro expression recognition without spotting (pseudo labeling). I found an error like this

"ValueError: Unexpected result of train_function (Empty logs). Please use Model.compile(..., run_eagerly=True), or tf.config.run_functions_eagerly(True) for more information of where went wrong, or file a issue/bug to tf.keras."

Inconsistent results

Dear author, it is an honor to have read your code. I would like to ask why my dataset and code are the same as yours, and why there is so much difference in accuracy after complete training. I trained myself twice using the dataset SMIC-NIR and SMIC-VIS, with SMIC-NIR having an Accuracy Score of 0.3684 and 0.5294, and SMIC-VIS having an Accuracy Score of 0.6667 and 0.4828, respectively, which is somewhat different from the accuracy in the author's paper, May I ask why this is