rework saving training params to file #6372

1 files changed, 7 insertions, 21 deletions

diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py
index 3237c37a..b0cfbe71 100644
--- a/modules/hypernetworks/hypernetwork.py
+++ b/modules/hypernetworks/hypernetwork.py
@@ -13,7 +13,7 @@ import tqdm
 from einops import rearrange, repeat

 from ldm.util import default

 from modules import devices, processing, sd_models, shared, sd_samplers

-from modules.textual_inversion import textual_inversion

+from modules.textual_inversion import textual_inversion, logging

 from modules.textual_inversion.learn_schedule import LearnRateScheduler

 from torch import einsum

 from torch.nn.init import normal_, xavier_normal_, xavier_uniform_, kaiming_normal_, kaiming_uniform_, zeros_

@@ -401,25 +401,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None,
     hypernet.save(fn)

 

     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):

     # images allows training previews to have infotext. Importing it at the top causes a circular import problem.

@@ -477,7 +459,11 @@ 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)

 

     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)

+        saved_params = dict(

+            model_name=checkpoint.model_name, model_hash=checkpoint.hash, num_of_dataset_images=len(ds),

+            **{field: getattr(hypernetwork, field) for field in ['layer_structure', 'activation_func', 'weight_init', 'add_layer_norm', 'use_dropout', ]}

+        )

+        logging.save_settings_to_file(log_directory, {**saved_params, **locals()})

 

     latent_sampling_method = ds.latent_sampling_method