Input size $= n_h^{[l-1]} \times n_w^{[l-1]} \times n_c^{[l-1]}$ Kernel size $= f_h^{[l]} \times f_w^{[l]} \times n_c^{[l]}$ Where $n_c^{[l]} =$ number of filters in layer $l$ because it should match the number of outputs. Stride size $= s_h^{[l]} \times s_w^{[l]}$ Padding size $= p_h^{[l]} \times p_w^{[l]}$

Output (Activations $a^{[l]}$) size $= n_h^{[l]} \times n_w^{[l]} \times n_c^{[l]}$ $n_h^{[l]} = \left \lfloor{ \frac{n_h^{[l-1]} + 2p_h^{[l]} − k_h^{[l]}}{s_h^{[l]}}}\right \rfloor + 1$ $n_w^{[l]} = \left \lfloor{ \frac{n_w^{[l-1]} + 2p_w^{[l]} − k_w^{[l]}}{s_w^{[l]}}}\right \rfloor + 1$

# of Parameters: Weights: $f_h^{[l]} \times f_w^{[l]} \times n_c^{[l-1]} \times n_c^{[l]}$ Bias: $n_c^{[l]}$