if LOGGING:
wandb.watch(policy)
optimizer = torch.optim.Adam(policy.parameters(), lr=params["LR"])
eps = np.finfo(np.float32).eps.item()
if not os.path.exists(exp_dir):
os.mkdir(exp_dir)
fixed_cam = npa([0, 0, 0])
for i_episode in trange(params["NUM_EPISODES"]):
# sample image
state = torch.Tensor(data_generator.sample()).permute(
2, 0, 1).unsqueeze(0).to(device)
env.base_light = -data_generator.light + 1
# encode to latent variables (mu/var)
latent_mu, latent_variance = policy.encode(state)
lmu_npy = latent_mu.detach().view(-1).cpu().numpy()
lva_npy = latent_variance.detach().view(-1).cpu().numpy()
if LOGGING:
wandb.log({
"mu mean": np.mean(lmu_npy),
"mu min": np.min(lmu_npy),
"mu max": np.max(lmu_npy),
"var mean": np.mean(lva_npy),
"var min": np.min(lva_npy),
"var max": np.max(lva_npy),
from threedee_tools.datasets import CubeLoader from threedee_tools.renderer import Renderer import numpy as np import matplotlib.pyplot as plt env = Renderer(128, 128, shape="ijcv") gen = CubeLoader() imga = gen.sample() print(gen.cam) print(gen.light) env.base_light = -gen.light + 1 imgb = env.render(np.ones((160)), np.array([0, 0, 0]), cam_pos=gen.cam + .7) imgb = np.array(imgb, dtype=np.float32) / 255 imgab = np.zeros((128, 128 * 2, 3), dtype=np.float32) imgab[:, :128, :] = imga imgab[:, 128:, :] = imgb plt.imshow(imgab) plt.show()
