mask_s, mask_s, comet_exp, True,
None, None)
else:
trainer.gen_update(images_as, images_bs, config,
mask_s, mask_s, comet_exp, True,
sem_a, sem_b)
if trainer.use_classifier_sr and (
iterations + 1
) % config["adaptation"]["classif_frequency"] == 0:
trainer.domain_classifier_sr_update(
images_as, images_bs, True,
config["adaptation"]["dfeat_lambda"],
iterations + 1, comet_exp)
if trainer.train_seg:
trainer.segmentation_head_update(
images_as, images_bs, sem_a, sem_b,
config['adaptation']['sem_seg_lambda'], comet_exp)
# Write images
if (iterations + 1) % config["image_save_iter"] == 0:
with torch.no_grad():
test_image_outputs = trainer.sample(
test_display_images_a, test_display_images_b)
train_image_outputs = trainer.sample(
train_display_images_a, train_display_images_b)
write_2images(
test_image_outputs,
display_size,
image_directory,
"test_%08d" % (iterations + 1),
comet_exp,
== 0):
trainer.domain_classifier_sr_update(
images_as,
images_bs,
mask_s,
True,
config["adaptation"]["dfeat_lambda"],
iterations + 1,
comet_exp,
)
if trainer.train_seg:
trainer.segmentation_head_update(
images_as,
images_bs,
mask_s,
sem_a,
sem_b,
config["adaptation"]["sem_seg_lambda"],
comet_exp,
)
if (iterations + 1) % config["image_save_iter"] == 0:
with torch.no_grad():
test_image_outputs = trainer.sample(
test_display_images_a,
test_display_images_b,
test_display_masks_a,
test_display_masks_b,
)
train_image_outputs = trainer.sample(
train_display_images_a,
