Lstm_cell_backward just one value not match

Course Q&A Deep Learning Specialization Sequence Models
1

My result mostly are close to the expected result. But the gradients["db?"][4] the are 10x bigger. What’s wrong?

gradients["dxt"][1][2] = 3.2305591151091875
gradients["dxt"].shape = (3, 10)
gradients["da_prev"][2][3] = -0.06396214197109236
gradients["da_prev"].shape = (5, 10)
gradients["dc_prev"][2][3] = 0.7975220387970015
gradients["dc_prev"].shape = (5, 10)
gradients["dWf"][3][1] = -0.1479548381644968
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 1.0574980552259903
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = 2.3045621636876668
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.3313115952892109
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [0.01886464]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.04014249]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [0.02558776]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [0.01389334]
gradients["dbo"].shape = (5, 1)

Expected output:

gradients["dxt"][1][2] = 3.23055911511
gradients["dxt"].shape = (3, 10)
gradients["da_prev"][2][3] = -0.0639621419711
gradients["da_prev"].shape = (5, 10)
gradients["dc_prev"][2][3] = 0.797522038797
gradients["dc_prev"].shape = (5, 10)
gradients["dWf"][3][1] = -0.147954838164
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 1.05749805523
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = 2.30456216369
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.331311595289
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [ 0.18864637]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.40142491]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [ 0.25587763]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [ 0.13893342]
gradients["dbo"].shape = (5, 1)
2

Figured out. I use np.mean instead of np.sum.

3 Likes