recon_imgs = torch.cat(recon_imgs)
compare = torch.cat((oirgin_imgs, recon_imgs.cpu().data))
save_image(compare.cpu(), output_path+'/fig1_3.jpg', nrow=10, normalize=True)
# fig1_4
imgs = []
for i in range(32):
z = Variable(torch.randn(1024).cuda())
out_img = model.decode(z)
imgs.append(out_img)
imgs = torch.cat(imgs)
save_image(imgs.cpu().data, output_path+'/fig1_4.jpg', nrow=8, normalize=True)
# fig1_5
data_for_tsne = torch.cat(data_for_tsne)
label_for_tsne = torch.cat(label_for_tsne).numpy()
mu, logvar = model.encode(Variable(data_for_tsne.cuda()))
latent_code = mu.cpu().data.numpy()
latent_emmbedded = TSNE(random_state=2).fit_transform(latent_code)
plt.figure()
# for i in [0,1]:
# if i:
# gender = 'Male'
# else:
# gender = 'Female'
# xy = latent_emmbedded[label_for_tsne==i]
# plt.scatter(xy[:,0], xy[:,1], c=i, label=gender)
plt.scatter(latent_emmbedded[:,0], latent_emmbedded[:,1], c=label_for_tsne)
# plt.legend()
plt.savefig(output_path+'/fig1_5.jpg')
sum([len(raw_transitions[i]) for i in range(n_trajs)]))
transitions = []
for i in range(n_trajs):
for t in range(len(raw_transitions[i]) - 1):
o, o_next, true_s, true_s_next = raw_transitions[i][t][0], \
raw_transitions[i][t + 1][0], \
raw_transitions[i][t][1]['state'], \
raw_transitions[i][t + 1][1]['state']
if o.sum() != 0 and o_next.sum() != 0:
with torch.no_grad():
if not is_image:
s = [np.array([1])]
s_next = [np.array([1])]
else:
s = model.encode(
Variable(
torch.cuda.FloatTensor(
np.transpose(o, (2, 0, 1))[None])))[1]
s_next = model.encode(
Variable(
torch.cuda.FloatTensor(
np.transpose(o_next, (2, 0, 1))[None])))[1]
if i == 0 and t == 0:
recon = model.decode(s)
import ipdb
ipdb.set_trace()
save_image(
torch.cat([
torch.cuda.FloatTensor(
np.transpose(o,
(2, 0, 1))[None]).cpu() /
255,