Worse performance when executing model.eval() than model.train()

[1chimaruGin (Ichimaru Gin)]

Saved CNN model giving different results

You could debug this by: def areTorchModulesEqual(module1, module2): for index, (p1, p2) in enumerate(zip(module1.parameters(), module2.parameters())): if p1.data.ne(p2.data).sum() > 0: return False return True def whichModulesHaveBeenUpdated(model1_list, model2_list): for index, module1 in enumerate(model1_list): module2 = model2_list[index] if areTorchModulesEqual(module1, module2): print("At Index " + str(index) + " Module1 and Mod…