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
↓ 2 callersMethodget_input
(self, batch, k)
ldm/models/diffusion/classifier.py:124
↓ 2 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, cond_key=None, retu
ldm/models/diffusion/ddpm.py:800
↓ 2 callersMethodget_input
Degradation pipeline, modified from Real-ESRGAN: https://github.com/xinntao/Real-ESRGAN
ldm/models/diffusion/ddpm.py:1923
↓ 2 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, cond_key=None, retu
ldm/models/diffusion/ddpm_inv.py:694
↓ 2 callersMethodget_input_synthesis
(self, batch, val=False, test_gt=False)
ldm/models/autoencoder.py:668
↓ 2 callersMethodget_learned_conditioning
(self, c)
ldm/models/diffusion/ddpm.py:1768
↓ 2 callersFunctionget_obj_from_str
(string, reload=False)
ldm/util.py:96
↓ 2 callersFunctiongroup_dict_by_key
(cond, d)
ldm/modules/x_transformer.py:93
↓ 2 callersFunctiongroupby_prefix_and_trim
(prefix, d)
ldm/modules/x_transformer.py:110
↓ 2 callersFunctioninit_dist
(launcher, backend='nccl', **kwargs)
basicsr/utils/dist_util.py:10
↓ 2 callersMethodinit_from_ckpt
(self, path, ignore_keys=list(), only_model=False)
ldm/models/diffusion/ddpm_inv.py:195
↓ 2 callersMethodinit_weights
(self)
basicsr/ops/dcn/deform_conv.py:322
↓ 2 callersFunctioninstantiate_from_config_sr
(config)
ldm/util.py:87
↓ 2 callersFunctionismap
(x)
ldm/util.py:41
↓ 2 callersFunctionload_img
(path)
scripts/sr_val_ddpm_text_T_vqganfin_facerefersampling.py:135
↓ 2 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
predict.py:202
↓ 2 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/sr_val_ddim_text_T_negativeprompt.py:115
↓ 2 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/sr_val_ddim_text_T_negativeprompt_canvas_tile.py:118
↓ 2 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas.py:85
↓ 2 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/sr_val_ddpm_text_T_vqganfin_old.py:82
↓ 2 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/sr_val_ddim_text_T_negativeprompt_canvas.py:116
↓ 2 callersFunctionload_model_from_config
(config, ckpt, verbose=False)
scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas_tile.py:87
↓ 2 callersMethodlog_img
(self, pl_module, batch, batch_idx, split="train")
main.py:342
↓ 2 callersFunctionmake_beta_schedule
(schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3)
ldm/modules/diffusionmodules/util.py:21
↓ 2 callersFunctionmake_ddim_sampling_parameters
(alphacums, ddim_timesteps, eta, verbose=True)
ldm/modules/diffusionmodules/util.py:63
↓ 2 callersFunctionmake_ddim_timesteps
(ddim_discr_method, num_ddim_timesteps, num_ddpm_timesteps, verbose=True)
ldm/modules/diffusionmodules/util.py:46
↓ 2 callersFunctionmake_exp_dirs
Make dirs for experiments.
basicsr/utils/misc.py:38
↓ 2 callersMethodmake_noise
(self, batch, num_noise)
basicsr/models/stylegan2_model.py:172
↓ 2 callersFunctionmkdir
(path)
ldm/modules/image_degradation/utils_image.py:153
↓ 2 callersMethodnext
(self)
basicsr/data/prefetch_dataloader.py:114
↓ 2 callersMethodnondist_validation
(self, dataloader, current_iter, tb_logger, save_img)
basicsr/models/sr_model.py:184
↓ 2 callersFunctionnorm_cdf
(x)
basicsr/archs/arch_util.py:277
↓ 2 callersFunctionordered_yaml
Support OrderedDict for yaml. Returns: tuple: yaml Loader and Dumper.
basicsr/utils/options.py:13
↓ 2 callersMethodp_sample
(self, x, c, t, clip_denoised=False, repeat_noise=False, return_codebook_ids=False, quantize_
ldm/models/diffusion/ddpm.py:1244
↓ 2 callersMethodp_sample
(self, x, c, struct_cond, t, clip_denoised=False, repeat_noise=False, return_codebook_ids=Fal
ldm/models/diffusion/ddpm.py:2729
↓ 2 callersMethodp_sample
(self, x, c, t, clip_denoised=False, repeat_noise=False, return_codebook_ids=False, quantize_
ldm/models/diffusion/ddpm_inv.py:1128
↓ 2 callersMethodp_sample_ddim
(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
ldm/models/diffusion/ddim.py:230
↓ 2 callersFunctionpaired_paths_from_folder
Generate paired paths from folders. Args: folders (list[str]): A list of folder path. The order of list should be [input_fold
basicsr/data/data_util.py:247
↓ 2 callersFunctionpaired_paths_from_lmdb
Generate paired paths from lmdb files. Contents of lmdb. Taking the `lq.lmdb` for example, the file structure is: :: lq.lmdb
basicsr/data/data_util.py:95
↓ 2 callersFunctionparse_options
(root_path, is_train=True)
basicsr/utils/options.py:99
↓ 2 callersFunctionpixel_unshuffle
Pixel unshuffle. Args: x (Tensor): Input feature with shape (b, c, hh, hw). scale (int): Downsample ratio. Returns:
basicsr/archs/arch_util.py:225
↓ 2 callersMethodpost_process
(self)
basicsr/utils/realesrgan_utils.py:162
↓ 2 callersMethodpre_process
Pre-process, such as pre-pad and mod pad, so that the images can be divisible
basicsr/utils/realesrgan_utils.py:68
↓ 2 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
ldm/models/diffusion/ddpm_inv.py:225
↓ 2 callersMethodpreprocess
(self, tensor_input)
basicsr/archs/spynet_arch.py:45
↓ 2 callersMethodprocess
(self)
basicsr/utils/realesrgan_utils.py:93
↓ 2 callersMethodq_mean_variance
Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of diff
ldm/models/diffusion/ddpm.py:325
↓ 2 callersMethodq_posterior
(self, x_start, x_t, t)
ldm/models/diffusion/ddpm_inv.py:231
↓ 2 callersFunctionquality_to_factor
Calculate factor corresponding to quality Args: quality(float): Quality for jpeg compression. Returns: float: Compression f
basicsr/utils/diffjpeg.py:32
↓ 2 callersMethodrandn_cropinput
(self, lq, gt, base_size=[64, 128, 256, 512])
ldm/models/diffusion/ddpm.py:1911
↓ 2 callersFunctionrandom_crop
(lq, hq, sf=4, lq_patchsize=64)
ldm/modules/image_degradation/bsrgan.py:427
↓ 2 callersFunctionrandom_generate_gaussian_noise
(img, sigma_range=(0, 10), gray_prob=0, return_sigma=False)
basicsr/data/degradations.py:565
↓ 2 callersFunctionrandom_mixed_kernels
Randomly generate mixed kernels. Args: kernel_list (tuple): a list name of kernel types, support ['iso', 'aniso', 'skew', 'ge
basicsr/data/degradations.py:336
↓ 2 callersFunctionread_image
(im_path)
scripts/sr_val_ddim_text_T_negativeprompt_canvas_tile.py:149
↓ 2 callersFunctionread_image
(im_path)
scripts/sr_val_ddpm_text_T_vqganfin_oldcanvas_tile.py:117
↓ 2 callersMethodrecord
(self)
basicsr/utils/logger.py:23
↓ 2 callersMethodregister_schedule
(self, given_betas=None, beta_schedule="linear", timesteps=1000, linear_start=1e-4,
ldm/models/diffusion/ddpm_inv.py:126
↓ 2 callersMethodreset_parameters
(self)
basicsr/ops/dcn/deform_conv.py:225
↓ 2 callersFunctionrgb2bgr
(im)
scripts/util_image.py:214
↓ 2 callersMethodsample
(self, cond, struct_cond, batch_size=16, return_intermediates=False, x_T=None, verbose=True, ti
ldm/models/diffusion/ddpm.py:3057
↓ 2 callersMethodsample
(self, batch_size=16, return_intermediates=False)
ldm/models/diffusion/ddpm_inv.py:277
↓ 2 callersMethodsave
Save networks and training state.
basicsr/models/base_model.py:32
↓ 2 callersMethodsave
(self, ckpt_path)
ldm/modules/embedding_manager.py:131
↓ 2 callersFunctionshift_pixel
shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir
ldm/modules/image_degradation/bsrgan_light.py:99
↓ 2 callersFunctionshift_pixel
shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir
ldm/modules/image_degradation/bsrgan.py:99
↓ 2 callersFunctionsizeof_fmt
Get human readable file size. Args: size (int): File size. suffix (str): Suffix. Default: 'B'. Return: str: Formatte
basicsr/utils/misc.py:127
↓ 2 callersMethodtile_process
It will first crop input images to tiles, and then process each tile. Finally, all the processed tiles are merged into one images. Mo
basicsr/utils/realesrgan_utils.py:97
↓ 2 callersMethodto_rgb
(self, x)
ldm/models/autoencoder.py:442
↓ 2 callersMethodto_rgb
(self, x)
ldm/models/diffusion/ddpm.py:1555
↓ 2 callersMethodupdate_gaussian
Input: pch_res: n x c x pch_size x pch_size, float index_infos: (h_start, h_end, w_start, w_end)
scripts/util_image.py:785
↓ 2 callersFunctionwavelet_decomposition
Apply wavelet decomposition to the input tensor. This function only returns the low frequency & the high frequency.
scripts/wavelet_color_fix.py:94
↓ 2 callersFunctionwindow_partition
Args: x: (b, h, w, c) window_size (int): window size Returns: windows: (num_windows*b, window_size, window_size, c)
basicsr/archs/swinir_arch.py:63
↓ 2 callersFunctionwindow_partition
Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)
ldm/modules/swinir.py:33
↓ 1 callersFunctionAttentionBlock
(in_channel)
basicsr/archs/dfdnet_util.py:91
↓ 1 callersMethod__init__
(self, opt, que, qid)
basicsr/utils/realesrgan_utils.py:278
↓ 1 callersMethod__init__
(self, load_path=None)
basicsr/archs/spynet_arch.py:36
↓ 1 callersMethod__init__
(self, num_in_ch, num_feat=64, skip_connection=True)
basicsr/archs/discriminator_arch.py:102
↓ 1 callersMethod__init__
(self, mid_channels=64, num_blocks=7, max_residue_magnitude
basicsr/archs/basicvsrpp_arch.py:43
↓ 1 callersMethod__init__
(self, num_feat, dict_path)
basicsr/archs/dfdnet_arch.py:67
↓ 1 callersMethod__init__
(self, opt)
basicsr/data/vimeo90k_dataset.py:59
↓ 1 callersMethod__init__
(self, opt)
basicsr/data/single_image_dataset.py:32
↓ 1 callersMethod__init__
(self, opt)
basicsr/data/reds_dataset.py:49
↓ 1 callersMethod__init__
(self, optimizer, milestones, gamma=0.1, restarts=(0, ), restart_weights=(1, ), last_epoch=-1)
basicsr/models/lr_scheduler.py:19
↓ 1 callersMethod__init__
(self, gan_type, real_label_val=1.0, fake_label_val=0.0, loss_weight=1.0)
basicsr/losses/gan_loss.py:23
↓ 1 callersMethod__iter__
(self)
basicsr/data/prefetch_dataloader.py:35
↓ 1 callersMethod__len__
(self)
scripts/util_image.py:641
↓ 1 callersMethod__len__
(self)
scripts/util_image.py:721
↓ 1 callersMethod__len__
(self)
basicsr/data/ffhq_dataset.py:79
↓ 1 callersMethod__len__
(self)
ldm/data/base.py:18
↓ 1 callersFunction_augment
(img)
basicsr/data/transforms.py:181
↓ 1 callersFunction_augment
(img)
ldm/modules/image_degradation/utils_image.py:475
↓ 1 callersFunction_augment_flow
(flow)
basicsr/data/transforms.py:190
↓ 1 callersMethod_build_causal_attention_mask
(self, bsz, seq_len, dtype)
ldm/modules/encoders/transformer_utils.py:174
↓ 1 callersMethod_dequeue_and_enqueue
It is the training pair pool for increasing the diversity in a batch. Batch processing limits the diversity of synthetic degradations in a ba
basicsr/models/realesrnet_model.py:31
↓ 1 callersMethod_dequeue_and_enqueue
It is the training pair pool for increasing the diversity in a batch. Batch processing limits the diversity of synthetic degradations in a ba
basicsr/models/realesrgan_model.py:32
↓ 1 callersMethod_dequeue_and_enqueue
It is the training pair pool for increasing the diversity in a batch. Batch processing limits the diversity of synthetic degradations in a ba
ldm/models/autoencoder.py:597
↓ 1 callersMethod_divide_pred
Take the prediction of fake and real images from the combined batch. The prediction contains the intermediate outputs of multiscale G
basicsr/models/hifacegan_model.py:98
↓ 1 callersMethod_filter_relpaths
(self, relpaths)
ldm/data/imagenet.py:48
↓ 1 callersMethod_gaussian_weights
Generates a gaussian mask of weights for tile contributions
scripts/util_image.py:753
↓ 1 callersMethod_gaussian_weights
Generates a gaussian mask of weights for tile contributions
ldm/models/diffusion/ddim.py:465
← previousnext →301–400 of 1,625, ranked by callers