From 9ceef81f77ecce89f0c8f412c4d849210d852e82 Mon Sep 17 00:00:00 2001 From: Muhammad Rizqi Nur Date: Fri, 28 Oct 2022 20:48:08 +0700 Subject: Fix log off by 1 --- modules/hypernetworks/hypernetwork.py | 12 +++++++----- modules/textual_inversion/learn_schedule.py | 2 +- modules/textual_inversion/textual_inversion.py | 24 ++++++++++++------------ 3 files changed, 20 insertions(+), 18 deletions(-) diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 8113b35b..a0297997 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -428,7 +428,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log optimizer.step() - if torch.isnan(losses[hypernetwork.step % losses.shape[0]]): + steps_done = hypernetwork.step + 1 + + if torch.isnan(losses[hypernetwork.step % losses.shape[0]]): raise RuntimeError("Loss diverged.") if len(previous_mean_losses) > 1: @@ -438,9 +440,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log dataset_loss_info = f"dataset loss:{mean(previous_mean_losses):.3f}" + u"\u00B1" + f"({std / (len(previous_mean_losses) ** 0.5):.3f})" pbar.set_description(dataset_loss_info) - if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0: + if hypernetwork_dir is not None and steps_done % save_hypernetwork_every == 0: # Before saving, change name to match current checkpoint. - hypernetwork.name = f'{hypernetwork_name}-{hypernetwork.step}' + hypernetwork.name = f'{hypernetwork_name}-{steps_done}' last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork.name}.pt') hypernetwork.save(last_saved_file) @@ -449,8 +451,8 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log "learn_rate": scheduler.learn_rate }) - if hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0: - forced_filename = f'{hypernetwork_name}-{hypernetwork.step}' + if images_dir is not None and steps_done % create_image_every == 0: + forced_filename = f'{hypernetwork_name}-{steps_done}' last_saved_image = os.path.join(images_dir, forced_filename) optimizer.zero_grad() diff --git a/modules/textual_inversion/learn_schedule.py b/modules/textual_inversion/learn_schedule.py index 2062726a..3a736065 100644 --- a/modules/textual_inversion/learn_schedule.py +++ b/modules/textual_inversion/learn_schedule.py @@ -52,7 +52,7 @@ class LearnRateScheduler: self.finished = False def apply(self, optimizer, step_number): - if step_number <= self.end_step: + if step_number < self.end_step: return try: diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index ff002d3e..17dfb223 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -184,9 +184,8 @@ def write_loss(log_directory, filename, step, epoch_len, values): if shared.opts.training_write_csv_every == 0: return - if step % shared.opts.training_write_csv_every != 0: + if (step + 1) % shared.opts.training_write_csv_every != 0: return - write_csv_header = False if os.path.exists(os.path.join(log_directory, filename)) else True with open(os.path.join(log_directory, filename), "a+", newline='') as fout: @@ -196,11 +195,11 @@ def write_loss(log_directory, filename, step, epoch_len, values): csv_writer.writeheader() epoch = step // epoch_len - epoch_step = step - epoch * epoch_len + epoch_step = step % epoch_len csv_writer.writerow({ "step": step + 1, - "epoch": epoch + 1, + "epoch": epoch, "epoch_step": epoch_step + 1, **values, }) @@ -282,15 +281,16 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc loss.backward() optimizer.step() + steps_done = embedding.step + 1 epoch_num = embedding.step // len(ds) - epoch_step = embedding.step - (epoch_num * len(ds)) + 1 + epoch_step = embedding.step % len(ds) - pbar.set_description(f"[Epoch {epoch_num}: {epoch_step}/{len(ds)}]loss: {losses.mean():.7f}") + pbar.set_description(f"[Epoch {epoch_num}: {epoch_step+1}/{len(ds)}]loss: {losses.mean():.7f}") - if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0: + if embedding_dir is not None and steps_done % save_embedding_every == 0: # Before saving, change name to match current checkpoint. - embedding.name = f'{embedding_name}-{embedding.step}' + embedding.name = f'{embedding_name}-{steps_done}' last_saved_file = os.path.join(embedding_dir, f'{embedding.name}.pt') embedding.save(last_saved_file) embedding_yet_to_be_embedded = True @@ -300,8 +300,8 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc "learn_rate": scheduler.learn_rate }) - if embedding.step > 0 and images_dir is not None and embedding.step % create_image_every == 0: - forced_filename = f'{embedding_name}-{embedding.step}' + if images_dir is not None and steps_done % create_image_every == 0: + forced_filename = f'{embedding_name}-{steps_done}' last_saved_image = os.path.join(images_dir, forced_filename) p = processing.StableDiffusionProcessingTxt2Img( sd_model=shared.sd_model, @@ -334,7 +334,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc if save_image_with_stored_embedding and os.path.exists(last_saved_file) and embedding_yet_to_be_embedded: - last_saved_image_chunks = os.path.join(images_embeds_dir, f'{embedding_name}-{embedding.step}.png') + last_saved_image_chunks = os.path.join(images_embeds_dir, f'{embedding_name}-{steps_done}.png') info = PngImagePlugin.PngInfo() data = torch.load(last_saved_file) @@ -350,7 +350,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc checkpoint = sd_models.select_checkpoint() footer_left = checkpoint.model_name footer_mid = '[{}]'.format(checkpoint.hash) - footer_right = '{}v {}s'.format(vectorSize, embedding.step) + footer_right = '{}v {}s'.format(vectorSize, steps_done) captioned_image = caption_image_overlay(image, title, footer_left, footer_mid, footer_right) captioned_image = insert_image_data_embed(captioned_image, data) -- cgit v1.2.1