bobingstern / microflow Goto Github PK

Hi,
I want to use this model
model = tf.keras.Sequential([
tf.keras.layers.Input(shape=(6,)),
tf.keras.layers.Dense(32, activation='relu'),
tf.keras.layers.Dense(32, activation='relu'),
tf.keras.layers.Dense(4, activation='softmax')
])
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),loss='mse')
to play snake game on an STM32. You mention that only Dense is implemented. Does Input can be implemented as a separate layer or must be included in Dense?

The python code works for building the model, however I cant get an output for saving the model parameters and weights to the txt file.

Hello, do you think it is possible to add training function?

Hello,

I tested the board_test and the XOR model but I get this error. I tried different cards and I got the same error each time.
Have you an idea how to fix this please?

undefined reference to `MicroMLP::MicroMLP(int, int*, double*, double*, int)'

Thank you