MCPcopy Create free account

hub / github.com/IceClear/StableSR / functions

Functions1,625 in github.com/IceClear/StableSR

⨍ Functions 1,625◇ Types & classes 334↳ Endpoints 1
↓ 1 callersFunctionimresize
imresize function same as MATLAB. It now only supports bicubic. The same scale applies for both height and width. Args: img (Ten
basicsr/utils/matlab_functions.py:86
↓ 1 callersFunctionimssave
imgs: list, N images of size WxHxC
ldm/modules/image_degradation/utils_image.py:112
↓ 1 callersMethodinit_
(self)
ldm/modules/x_transformer.py:31
↓ 1 callersMethodinit_
(self)
ldm/modules/x_transformer.py:595
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list())
ldm/models/autoencoder.py:86
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/autoencoder.py:319
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/autoencoder.py:551
↓ 1 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/diffusion/classifier.py:70
↓ 1 callersMethodinit_offset
(self)
basicsr/ops/dcn/deform_conv.py:279
↓ 1 callersMethodinit_offset
(self)
basicsr/archs/basicvsrpp_arch.py:382
↓ 1 callersFunctioninit_tb_logger
(log_dir)
basicsr/utils/logger.py:119
↓ 1 callersFunctioninit_tb_loggers
(opt)
basicsr/train.py:17
↓ 1 callersMethodinit_training_settings
(self)
basicsr/models/sr_model.py:35
↓ 1 callersMethodinit_training_settings
(self)
basicsr/models/stylegan2_model.py:42
↓ 1 callersFunctioninit_wandb_logger
We now only use wandb to sync tensorboard log.
basicsr/utils/logger.py:126
↓ 1 callersMethodinit_weights
(self)
basicsr/ops/dcn/deform_conv.py:367
↓ 1 callersMethodinit_weights
Initialize weights for PixelShufflePack.
basicsr/archs/arch_util.py:88
↓ 1 callersFunctioninsert_bn
Insert bn layer after each conv. Args: names (list): The list of layer names. Returns: list: The list of layer names with bn
basicsr/archs/vgg_arch.py:36
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
ldm/models/diffusion/ddpm.py:655
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
ldm/models/diffusion/ddpm.py:1719
↓ 1 callersMethodinstantiate_cond_stage
(self, config)
ldm/models/diffusion/ddpm_inv.py:540
↓ 1 callersMethodinstantiate_embedding_manager
(self, config, embedder)
ldm/models/diffusion/ddpm_inv.py:562
↓ 1 callersMethodinstantiate_first_stage
(self, config)
ldm/models/diffusion/ddpm.py:648
↓ 1 callersMethodinstantiate_first_stage
(self, config)
ldm/models/diffusion/ddpm.py:1712
↓ 1 callersMethodinstantiate_first_stage
(self, config)
ldm/models/diffusion/ddpm_inv.py:533
↓ 1 callersMethodinstantiate_pretrained
(self, config)
ldm/modules/diffusionmodules/model.py:1076
↓ 1 callersMethodinstantiate_structcond_stage
(self, config)
ldm/models/diffusion/ddpm.py:1742
↓ 1 callersFunctionis_image_file
(filename)
ldm/modules/image_degradation/utils_image.py:29
↓ 1 callersFunctionisimage
(x)
ldm/util.py:47
↓ 1 callersMethodkl
(self, other=None)
ldm/modules/distributions/distributions.py:39
↓ 1 callersFunctionl1_loss
(pred, target)
basicsr/losses/basic_loss.py:13
↓ 1 callersFunctionlip2d
(x, logit, kernel=3, stride=2, padding=1)
basicsr/archs/hifacegan_util.py:154
↓ 1 callersMethodload_classifier
(self, ckpt_path, pool)
ldm/models/diffusion/classifier.py:95
↓ 1 callersMethodload_diffusion
(self)
ldm/models/diffusion/classifier.py:88
↓ 1 callersFunctionload_img
(path)
predict.py:271
↓ 1 callersFunctionload_img
(path)
app.py:65
↓ 1 callersFunctionload_img
(path)
scripts/sr_val_ddim_text_T_negativeprompt.py:135
↓ 1 callersFunctionload_img
(path)
scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas.py:104
↓ 1 callersFunctionload_img
(path)
scripts/sr_val_ddpm_text_T_vqganfin_old.py:101
↓ 1 callersFunctionload_img
(path)
scripts/sr_val_ddim_text_T_negativeprompt_canvas.py:136
↓ 1 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/generate_vqgan_data_face.py:119
↓ 1 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/generate_vqgan_data.py:119
↓ 1 callersFunctionload_resume_state
(opt)
basicsr/train.py:68
↓ 1 callersMethodlog_images
(self, batch, only_inputs=False, plot_ema=False, **kwargs)
ldm/models/autoencoder.py:241
↓ 1 callersMethodlog_images
(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs)
ldm/models/diffusion/ddpm.py:520
↓ 1 callersMethodlog_images
(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs)
ldm/models/diffusion/ddpm_inv.py:387
↓ 1 callersMethodlog_local
(self, save_dir, split, images, global_step, current_epoch, batch_idx)
main.py:323
↓ 1 callersFunctionmain
()
scripts/sr_val_ddim_text_T_negativeprompt.py:147
↓ 1 callersFunctionmain
()
scripts/sr_val_ddim_text_T_negativeprompt_canvas_tile.py:157
↓ 1 callersFunctionmain
()
scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas.py:116
↓ 1 callersFunctionmain
()
scripts/sr_val_ddpm_text_T_vqganfin_old.py:113
↓ 1 callersFunctionmain
()
scripts/sr_val_ddim_text_T_negativeprompt_canvas.py:148
↓ 1 callersFunctionmain
()
scripts/generate_vqgan_data_face.py:151
↓ 1 callersFunctionmain
()
scripts/sr_val_ddpm_text_T_vqganfin_facerefersampling.py:147
↓ 1 callersFunctionmain
()
scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas_tile.py:125
↓ 1 callersFunctionmain
()
scripts/generate_vqgan_data.py:151
↓ 1 callersMethodmake_cond_schedule
(self, )
ldm/models/diffusion/ddpm.py:617
↓ 1 callersMethodmake_cond_schedule
(self, )
ldm/models/diffusion/ddpm.py:1681
↓ 1 callersMethodmake_cond_schedule
(self, )
ldm/models/diffusion/ddpm_inv.py:501
↓ 1 callersMethodmake_schedule
(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True)
ldm/models/diffusion/plms.py:24
↓ 1 callersFunctionmax_neg_value
(tensor)
ldm/modules/x_transformer.py:82
↓ 1 callersFunctionmeasure_perplexity
(predicted_indices, n_embed)
ldm/modules/losses/vqperceptual.py:26
↓ 1 callersFunctionmelk
(*args, **kwargs)
main.py:716
↓ 1 callersMethodmeshgrid
(self, h, w)
ldm/models/diffusion/ddpm.py:1781
↓ 1 callersMethodmeshgrid
(self, h, w)
ldm/models/diffusion/ddpm_inv.py:604
↓ 1 callersFunctionmod_crop
Mod crop images, used during testing. Args: img (ndarray): Input image. scale (int): Scale factor. Returns: ndarray:
basicsr/data/transforms.py:6
↓ 1 callersFunctionmse_loss
(pred, target)
basicsr/losses/basic_loss.py:18
↓ 1 callersFunctionniqe
Calculate NIQE (Natural Image Quality Evaluator) metric. ``Paper: Making a "Completely Blind" Image Quality Analyzer`` This implementation c
basicsr/metrics/niqe.py:68
↓ 1 callersFunctionnondefault_trainer_args
(opt)
main.py:128
↓ 1 callersMethodnondist_validation
(self, dataloader, current_iter, tb_logger, save_img)
basicsr/models/stylegan2_model.py:265
↓ 1 callersMethodnondist_validation
TODO: Validation using updated metric system The metrics are now evaluated after all images have been tested This allows batc
basicsr/models/hifacegan_model.py:216
↓ 1 callersFunctionnot_equals
(val)
ldm/modules/x_transformer.py:70
↓ 1 callersMethodoptimize_parameters
(self, current_iter)
basicsr/models/sr_model.py:92
↓ 1 callersMethodp_losses
(self, x_start, t, noise=None)
ldm/models/diffusion/ddpm.py:434
↓ 1 callersMethodp_losses
(self, x_start, cond, t, noise=None)
ldm/models/diffusion/ddpm.py:1173
↓ 1 callersMethodp_losses
(self, x_start, cond, struct_cond, t, t_ori, z_gt, noise=None)
ldm/models/diffusion/ddpm.py:2450
↓ 1 callersMethodp_losses
(self, x_start, t, noise=None)
ldm/models/diffusion/ddpm_inv.py:303
↓ 1 callersMethodp_losses
(self, x_start, cond, t, noise=None)
ldm/models/diffusion/ddpm_inv.py:1053
↓ 1 callersMethodp_mean_variance
(self, x, t, clip_denoised: bool)
ldm/models/diffusion/ddpm.py:352
↓ 1 callersMethodp_mean_variance
(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
ldm/models/diffusion/ddpm.py:1210
↓ 1 callersMethodp_mean_variance
(self, x, c, struct_cond, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
ldm/models/diffusion/ddpm.py:2502
↓ 1 callersMethodp_mean_variance
(self, x, t, clip_denoised: bool)
ldm/models/diffusion/ddpm_inv.py:240
↓ 1 callersMethodp_mean_variance
(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
ldm/models/diffusion/ddpm_inv.py:1096
↓ 1 callersMethodp_mean_variance_canvas
(self, x, c, struct_cond, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
ldm/models/diffusion/ddpm.py:2567
↓ 1 callersMethodp_sample
(self, x, t, clip_denoised=True, repeat_noise=False)
ldm/models/diffusion/ddpm.py:367
↓ 1 callersMethodp_sample
(self, x, t, clip_denoised=True, repeat_noise=False)
ldm/models/diffusion/ddpm_inv.py:253
↓ 1 callersMethodp_sample_canvas
(self, x, c, struct_cond, t, clip_denoised=False, repeat_noise=False, return_codebook_ids=Fal
ldm/models/diffusion/ddpm.py:2764
↓ 1 callersMethodp_sample_ddim_sr_t
(self, x, c, struct_c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
ldm/models/diffusion/ddim.py:420
↓ 1 callersMethodp_sample_ddim_sr_tcanvas
(self, x, c, struct_c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
ldm/models/diffusion/ddim.py:543
↓ 1 callersMethodp_sample_loop
(self, shape, return_intermediates=False)
ldm/models/diffusion/ddpm.py:376
↓ 1 callersMethodp_sample_loop
(self, cond, shape, return_intermediates=False, x_T=None, verbose=True, callback=None, t
ldm/models/diffusion/ddpm.py:1331
↓ 1 callersMethodp_sample_loop
(self, cond, struct_cond, shape, return_intermediates=False, x_T=None, verbose=True, cal
ldm/models/diffusion/ddpm.py:2856
↓ 1 callersMethodp_sample_loop
(self, shape, return_intermediates=False)
ldm/models/diffusion/ddpm_inv.py:262
↓ 1 callersMethodp_sample_loop
(self, cond, shape, return_intermediates=False, x_T=None, verbose=True, callback=None, t
ldm/models/diffusion/ddpm_inv.py:1215
↓ 1 callersMethodp_sample_loop_canvas
(self, cond, struct_cond, shape, return_intermediates=False, x_T=None, verbose=True, cal
ldm/models/diffusion/ddpm.py:2978
↓ 1 callersMethodp_sample_plms
(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
ldm/models/diffusion/plms.py:173
↓ 1 callersMethodpad_spatial
Apply padding spatially. Since the PCD module in EDVR requires that the resolution is a multiple of 4, we apply padding to the input
basicsr/archs/basicvsr_arch.py:169
↓ 1 callersFunctionpaired_paths_from_meta_info_file_2
Generate paired paths from an meta information file. Each line in the meta information file contains the image names and image shape (usually
basicsr/data/data_util.py:199
↓ 1 callersFunctionpatches_from_image
(img, p_size=512, p_overlap=64, p_max=800)
ldm/modules/image_degradation/utils_image.py:93
↓ 1 callersFunctionpaths_from_lmdb
Generate paths from lmdb. Args: folder (str): Folder path. Returns: list[str]: Returned path list.
basicsr/data/data_util.py:298
← previousnext →501–600 of 1,625, ranked by callers