# create a recurrent NN
rnn = HessianRNN(layers=[lay[0], lay[1], lay[3]], struc_damping=0.5,
use_GPU=False, debug=False, loadW = wFileString)
#create an output file for the activations. I don't actually use this yet.
# out2 = open("activations", "wb+")
# shows activations for each time step for each input
index = 1
for i, t in zip(inputs, targets):
j = np.asarray(i)
# print >> out2, "\nTrail Num: {}".format(index)
index += 1
hidden = rnn.forward(j, rnn.W)[-2]
out = rnn.forward(j, rnn.W)[-1]
# for x in range(len(output)):
# for y in range(len(output[x][0])):
# if output[x][0][y] < 0.001:
# output[x][0][y] = 0
hidden = hidden[:, 0, :]
out = out[:, 0, :]
side = int(math.sqrt(len(hidden[0])))
hidden_sqr = np.zeros((side, side))
for x in range(len(hidden)):
plt.subplot(4, 4, x + 1) # the sublpot is 4x4 because the trial has 13 time steps (smallest perfect squre > 13)
for y in range(side):
hidden_sqr[y, :] = hidden[x][side*y:(side*y + side)]
print (side*y + side)
plt.pcolor(hidden_sqr)
