|
|
@ -526,7 +526,7 @@ for iteration in range(n_iter):
|
|
|
|
# In case we reached the last 75% of iterations,
|
|
|
|
# In case we reached the last 75% of iterations,
|
|
|
|
# decrease the learning rate of the optimizer 10-fold.
|
|
|
|
# decrease the learning rate of the optimizer 10-fold.
|
|
|
|
if iteration == round(n_iter * 0.75):
|
|
|
|
if iteration == round(n_iter * 0.75):
|
|
|
|
print("Decreasing LR 10-fold ...")
|
|
|
|
tqdm.write("Decreasing LR 10-fold ...")
|
|
|
|
optimizer = torch.optim.Adam(
|
|
|
|
optimizer = torch.optim.Adam(
|
|
|
|
neural_radiance_field.parameters(), lr=lr * 0.1
|
|
|
|
neural_radiance_field.parameters(), lr=lr * 0.1
|
|
|
|
)
|
|
|
|
)
|
|
|
@ -596,7 +596,7 @@ for iteration in range(n_iter):
|
|
|
|
|
|
|
|
|
|
|
|
# Every 10 iterations, print the current values of the losses.
|
|
|
|
# Every 10 iterations, print the current values of the losses.
|
|
|
|
if iteration % 10 == 0:
|
|
|
|
if iteration % 10 == 0:
|
|
|
|
print(
|
|
|
|
tqdm.write(
|
|
|
|
f"Iteration {iteration:05d}:"
|
|
|
|
f"Iteration {iteration:05d}:"
|
|
|
|
+ f" loss color = {float(color_err):1.2e}"
|
|
|
|
+ f" loss color = {float(color_err):1.2e}"
|
|
|
|
+ f" loss silhouette = {float(sil_err):1.2e}"
|
|
|
|
+ f" loss silhouette = {float(sil_err):1.2e}"
|
|
|
|