I'm trying to run this code for a people counting algorithm.
model = build_model()
epoch = 50
print("total epoch ", epoch)
model.fit(x=train_dataset, shuffle=True, epochs=epoch)
save_model(model, MODEL_PATH, MODEL_JSON_PATH)
sys.stdout.flush()
After executing the command, I get this error message:
Incompatible shapes: [1,14,14,1] vs. [1,28,28,1]
[[{{node gradient_tape/mean_squared_error/BroadcastGradientArgs}}]] [Op:__inference_train_function_136758]