Merge pull request #6372 from timntorres/save-ti-hypernet-settings-to-txt-revised

Save hypernet and textual inversion settings to text file, revised.
This commit is contained in:
AUTOMATIC1111 2023-01-06 07:59:44 +03:00 committed by GitHub
commit 88e01b237e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 49 additions and 3 deletions

View File

@ -401,7 +401,25 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
hypernet.save(fn) hypernet.save(fn)
shared.reload_hypernetworks() shared.reload_hypernetworks()
# Note: textual_inversion.py has a nearly identical function of the same name.
def save_settings_to_file(model_name, model_hash, initial_step, num_of_dataset_images, hypernetwork_name, layer_structure, activation_func, weight_init, add_layer_norm, use_dropout, learn_rate, batch_size, data_root, log_directory, training_width, training_height, steps, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# Starting index of preview-related arguments.
border_index = 21
# Get a list of the argument names.
arg_names = inspect.getfullargspec(save_settings_to_file).args
# Create a list of the argument names to include in the settings string.
names = arg_names[:border_index] # Include all arguments up until the preview-related ones.
if preview_from_txt2img:
names.extend(arg_names[border_index:]) # Include preview-related arguments if applicable.
# Build the settings string.
settings_str = "datetime : " + datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S") + "\n"
for name in names:
if name != 'log_directory': # It's useless and redundant to save log_directory.
value = locals()[name]
settings_str += f"{name}: {value}\n"
# Create or append to the file.
with open(os.path.join(log_directory, 'settings.txt'), "a+") as fout:
fout.write(settings_str + "\n\n")
def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height): def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# images allows training previews to have infotext. Importing it at the top causes a circular import problem. # images allows training previews to have infotext. Importing it at the top causes a circular import problem.
@ -458,6 +476,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, gradient_step,
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method) ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method)
if shared.opts.save_training_settings_to_txt:
save_settings_to_file(checkpoint.model_name, '[{}]'.format(checkpoint.hash), initial_step, len(ds), hypernetwork_name, hypernetwork.layer_structure, hypernetwork.activation_func, hypernetwork.weight_init, hypernetwork.add_layer_norm, hypernetwork.use_dropout, learn_rate, batch_size, data_root, log_directory, training_width, training_height, steps, create_image_every, save_hypernetwork_every, template_file, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height)
latent_sampling_method = ds.latent_sampling_method latent_sampling_method = ds.latent_sampling_method
dl = modules.textual_inversion.dataset.PersonalizedDataLoader(ds, latent_sampling_method=latent_sampling_method, batch_size=ds.batch_size, pin_memory=pin_memory) dl = modules.textual_inversion.dataset.PersonalizedDataLoader(ds, latent_sampling_method=latent_sampling_method, batch_size=ds.batch_size, pin_memory=pin_memory)

View File

@ -362,6 +362,7 @@ options_templates.update(options_section(('training', "Training"), {
"unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."), "unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."),
"pin_memory": OptionInfo(False, "Turn on pin_memory for DataLoader. Makes training slightly faster but can increase memory usage."), "pin_memory": OptionInfo(False, "Turn on pin_memory for DataLoader. Makes training slightly faster but can increase memory usage."),
"save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training of embedding or HN can be resumed with the matching optim file."), "save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training of embedding or HN can be resumed with the matching optim file."),
"save_training_settings_to_txt": OptionInfo(False, "Save textual inversion and hypernet settings to a text file whenever training starts."),
"dataset_filename_word_regex": OptionInfo("", "Filename word regex"), "dataset_filename_word_regex": OptionInfo("", "Filename word regex"),
"dataset_filename_join_string": OptionInfo(" ", "Filename join string"), "dataset_filename_join_string": OptionInfo(" ", "Filename join string"),
"training_image_repeats_per_epoch": OptionInfo(1, "Number of repeats for a single input image per epoch; used only for displaying epoch number", gr.Number, {"precision": 0}), "training_image_repeats_per_epoch": OptionInfo(1, "Number of repeats for a single input image per epoch; used only for displaying epoch number", gr.Number, {"precision": 0}),

View File

@ -1,6 +1,7 @@
import os import os
import sys import sys
import traceback import traceback
import inspect
import torch import torch
import tqdm import tqdm
@ -230,6 +231,26 @@ def write_loss(log_directory, filename, step, epoch_len, values):
**values, **values,
}) })
# Note: hypernetwork.py has a nearly identical function of the same name.
def save_settings_to_file(model_name, model_hash, initial_step, num_of_dataset_images, embedding_name, vectors_per_token, learn_rate, batch_size, data_root, log_directory, training_width, training_height, steps, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# Starting index of preview-related arguments.
border_index = 18
# Get a list of the argument names.
arg_names = inspect.getfullargspec(save_settings_to_file).args
# Create a list of the argument names to include in the settings string.
names = arg_names[:border_index] # Include all arguments up until the preview-related ones.
if preview_from_txt2img:
names.extend(arg_names[border_index:]) # Include preview-related arguments if applicable.
# Build the settings string.
settings_str = "datetime : " + datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S") + "\n"
for name in names:
if name != 'log_directory': # It's useless and redundant to save log_directory.
value = locals()[name]
settings_str += f"{name}: {value}\n"
# Create or append to the file.
with open(os.path.join(log_directory, 'settings.txt'), "a+") as fout:
fout.write(settings_str + "\n\n")
def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, data_root, template_file, steps, save_model_every, create_image_every, log_directory, name="embedding"): def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, data_root, template_file, steps, save_model_every, create_image_every, log_directory, name="embedding"):
assert model_name, f"{name} not selected" assert model_name, f"{name} not selected"
assert learn_rate, "Learning rate is empty or 0" assert learn_rate, "Learning rate is empty or 0"
@ -293,8 +314,8 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
if initial_step >= steps: if initial_step >= steps:
shared.state.textinfo = "Model has already been trained beyond specified max steps" shared.state.textinfo = "Model has already been trained beyond specified max steps"
return embedding, filename return embedding, filename
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else \ clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else \
torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else \ torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else \
None None
@ -308,6 +329,9 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method) ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method)
if shared.opts.save_training_settings_to_txt:
save_settings_to_file(checkpoint.model_name, '[{}]'.format(checkpoint.hash), initial_step, len(ds), embedding_name, len(embedding.vec), learn_rate, batch_size, data_root, log_directory, training_width, training_height, steps, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height)
latent_sampling_method = ds.latent_sampling_method latent_sampling_method = ds.latent_sampling_method
dl = modules.textual_inversion.dataset.PersonalizedDataLoader(ds, latent_sampling_method=latent_sampling_method, batch_size=ds.batch_size, pin_memory=pin_memory) dl = modules.textual_inversion.dataset.PersonalizedDataLoader(ds, latent_sampling_method=latent_sampling_method, batch_size=ds.batch_size, pin_memory=pin_memory)