MCPcopy Create free account

hub / github.com/MegaScenes/nvs / functions

Functions1,032 in github.com/MegaScenes/nvs

⨍ Functions 1,032◇ Types & classes 170
↓ 3 callersMethod__init__
(self, factor, output_size, initial_size=None, image_key="jpg")
ldm/data/laion.py:225
↓ 3 callersMethod__init__
(self, ddconfig, lossconfig, n_embed, embe
ldm/models/autoencoder.py:16
↓ 3 callersFunctionadd_blur
(img, sf=4)
ldm/modules/image_degradation/bsrgan_light.py:325
↓ 3 callersFunctioncheckpoint
Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas
ldm/modules/diffusionmodules/util.py:102
↓ 3 callersFunctioncreate_window
(window_size, channel)
ldm/modules/evaluate/ssim.py:22
↓ 3 callersFunctiondefault
(val, d)
ldm/modules/attention.py:20
↓ 3 callersFunctiondepth2pcd
(depth, K, C2W)
dataloader/util_3dphoto.py:54
↓ 3 callersMethodencode_first_stage
(self, x)
ldm/models/diffusion/ddpm.py:974
↓ 3 callersFunctionexists
(val)
ldm/modules/attention.py:12
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
ldm/modules/image_degradation/bsrgan_light.py:210
↓ 3 callersFunctionfspecial
python code from: https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filte
ldm/modules/image_degradation/bsrgan.py:210
↓ 3 callersMethodget_fold_unfold
:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
ldm/models/diffusion/ddpm.py:722
↓ 3 callersMethodget_fold_unfold
:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
ldm/models/diffusion/backup_ddpm.py:669
↓ 3 callersMethodget_fold_unfold
:param x: img of size (bs, c, h, w) :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
ldm/models/diffusion/all_functions_ddpm.py:695
↓ 3 callersMethodget_input
(self, batch, k)
ldm/models/autoencoder.py:125
↓ 3 callersMethodget_input
(self, batch, k)
ldm/models/autoencoder.py:346
↓ 3 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, return_original_img=False,
ldm/models/diffusion/ddpm.py:776
↓ 3 callersMethodget_input
(self, batch, k, return_first_stage_outputs=False, force_c_encode=False, return_original_img=False,
ldm/models/diffusion/all_functions_ddpm.py:749
↓ 3 callersMethodget_loss
(self, pred, target, mean=True)
ldm/models/diffusion/ddpm.py:330
↓ 3 callersMethodget_loss
(self, pred, target, mean=True)
ldm/models/diffusion/backup_ddpm.py:330
↓ 3 callersMethodget_loss
(self, pred, target, mean=True)
ldm/models/diffusion/all_functions_ddpm.py:330
↓ 3 callersMethodget_weighting
(self, h, w, Ly, Lx, device)
ldm/models/diffusion/ddpm.py:706
↓ 3 callersMethodget_weighting
(self, h, w, Ly, Lx, device)
ldm/models/diffusion/backup_ddpm.py:653
↓ 3 callersMethodget_weighting
(self, h, w, Ly, Lx, device)
ldm/models/diffusion/all_functions_ddpm.py:679
↓ 3 callersMethodmake_loader
(self, dataset_config, train=True)
ldm/data/laion.py:125
↓ 3 callersFunctionmake_tranforms
(image_transforms)
ldm/data/backup_simple.py:103
↓ 3 callersFunctionmean_flat
Take the mean over all non-batch dimensions.
ldm/modules/diffusionmodules/util.py:192
↓ 3 callersFunctionnormal_kl
source: https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/losses.py#L12 Compute the K
ldm/modules/distributions/distributions.py:65
↓ 3 callersFunctionperceptual_sim
(img1, img2, vgg16)
ldm/modules/evaluate/evaluate_perceptualsim.py:328
↓ 3 callersMethodpredict_start_from_noise
(self, x_t, t, noise)
ldm/models/diffusion/all_functions_ddpm.py:267
↓ 3 callersMethodprocess_im
(self, im)
ldm/data/backup_simple.py:411
↓ 3 callersFunctionpsnr
(img1, img2, mask=None,reshape=False)
ldm/modules/evaluate/evaluate_perceptualsim.py:304
↓ 3 callersFunctionrender_view
(H, W, K, C2W, mesh, ref_C2W=None)
dataloader/util_3dphoto.py:129
↓ 3 callersMethodsample
(self, S, batch_size, shape, conditioning=None,
ldm/models/diffusion/ddim.py:67
↓ 3 callersFunctionsave_images_as_grid
Save a grid of images with a maximum number of images per row. :param imgs: List of NumPy images :param fixed_height: Fixed height for e
dataloader/evalhelpers.py:198
↓ 3 callersMethodshared_step
(self, batch)
ldm/models/diffusion/ddpm.py:388
↓ 3 callersMethodshared_step
(self, batch)
ldm/models/diffusion/backup_ddpm.py:388
↓ 3 callersMethodshared_step
(self, batch)
ldm/models/diffusion/all_functions_ddpm.py:388
↓ 3 callersFunctionssim
(img1, img2)
ldm/modules/image_degradation/utils_image.py:669
↓ 3 callersFunctionssim_metric
(img1, img2, mask=None)
ldm/modules/evaluate/evaluate_perceptualsim.py:299
↓ 3 callersMethodto_rgb
(self, x)
ldm/models/autoencoder.py:256
↓ 3 callersMethodto_rgb
(self, x)
ldm/models/diffusion/ddpm.py:1711
↓ 3 callersMethodupdate
Compute generative metrics such as FID, KID, and IS. Args: ref (numpy array): _description_ trg (_type_): _descripti
evaluation/gen_metrics.py:57
↓ 2 callersFunctionNormalize
(in_channels)
ldm/modules/attention.py:77
↓ 2 callersMethod__init__
Returns only captions with dummy images
ldm/data/backup_simple.py:475
↓ 2 callersMethod__init__
(self, unet_config, timesteps=1000, beta_schedule="linear",
ldm/models/diffusion/ddpm.py:50
↓ 2 callersMethod__init__
(self, unet_config, timesteps=1000, beta_schedule="linear",
ldm/models/diffusion/all_functions_ddpm.py:50
↓ 2 callersMethod__init__
(self, channels, reduction)
ldm/thirdp/psp/helpers.py:59
↓ 2 callersFunction_batch_pairwise_distances
Compute pairwise distances between two batches of feature vectors.
ldm/modules/evaluate/adm_evaluator.py:436
↓ 2 callersFunction_download_inception_model
()
ldm/modules/evaluate/adm_evaluator.py:595
↓ 2 callersMethod_get_denoise_row_from_list
(self, samples, desc='', force_no_decoder_quantization=False)
ldm/models/diffusion/ddpm.py:650
↓ 2 callersMethod_get_denoise_row_from_list
(self, samples, desc='', force_no_decoder_quantization=False)
ldm/models/diffusion/all_functions_ddpm.py:624
↓ 2 callersMethod_get_rows_from_list
(self, samples)
ldm/models/diffusion/ddpm.py:432
↓ 2 callersMethod_get_rows_from_list
(self, samples)
ldm/models/diffusion/backup_ddpm.py:430
↓ 2 callersMethod_get_rows_from_list
(self, samples)
ldm/models/diffusion/all_functions_ddpm.py:432
↓ 2 callersMethod_load_im
(self, filename)
ldm/data/backup_simple.py:164
↓ 2 callersFunction_ssim
( img1, img2, window, window_size, channel, mask=None, size_average=True )
ldm/modules/evaluate/ssim.py:31
↓ 2 callersMethod_validation_step
(self, batch, batch_idx, suffix="")
ldm/models/autoencoder.py:171
↓ 2 callersFunctionadd_Gaussian_noise
(img, noise_level1=2, noise_level2=25)
ldm/modules/image_degradation/bsrgan_light.py:373
↓ 2 callersFunctionadd_Poisson_noise
(img)
ldm/modules/image_degradation/bsrgan.py:404
↓ 2 callersFunctionadd_resize
(img, sf=4)
ldm/modules/image_degradation/bsrgan.py:339
↓ 2 callersFunctionadd_speckle_noise
(img, noise_level1=2, noise_level2=25)
ldm/modules/image_degradation/bsrgan.py:386
↓ 2 callersFunctionalways
(val)
ldm/modules/x_transformer.py:64
↓ 2 callersMethodapply_model
(self, x_noisy, t, cond, return_ids=False)
ldm/models/diffusion/backup_ddpm.py:898
↓ 2 callersMethodapply_model
(self, x_noisy, t, cond, return_ids=False, return_feature=False)
ldm/models/diffusion/all_functions_ddpm.py:950
↓ 2 callersFunctionbicubic_degradation
Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image
ldm/modules/image_degradation/bsrgan_light.py:228
↓ 2 callersFunctionbicubic_degradation
Args: x: HxWxC image, [0, 1] sf: down-scale factor Return: bicubicly downsampled LR image
ldm/modules/image_degradation/bsrgan.py:228
↓ 2 callersFunctioncartesian_to_spherical
(xyz)
dataloader/data_helpers.py:659
↓ 2 callersFunctioncartesian_to_spherical
(xyz)
ldm/data/common.py:35
↓ 2 callersMethodcartesian_to_spherical
(self, xyz)
ldm/data/backup_simple.py:248
↓ 2 callersFunctioncartesian_to_spherical_torch
(xyz)
ldm/data/common.py:74
↓ 2 callersMethodcompute
(self, aggregate=None)
evaluation/gen_metrics.py:38
↓ 2 callersMethodcompute
(self, aggregation="mean")
evaluation/recon_metrics.py:51
↓ 2 callersMethodcompute_activations
Compute image features for downstream evals. :param batches: a iterator over NHWC numpy arrays in [0, 255]. :return: a tuple
ldm/modules/evaluate/adm_evaluator.py:163
↓ 2 callersFunctioncompute_stats
(feats: np.ndarray)
ldm/modules/evaluate/torch_frechet_video_distance.py:34
↓ 2 callersMethodconvert_path_to_your_path
path 1, path2 in self.paired_images are absolute paths that should be converted to your local paths format of path1, path2: '/share/p
dataloader/paired_dataset.py:55
↓ 2 callersFunctioncount_flops_attn
A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr
ldm/modules/diffusionmodules/openaimodel.py:329
↓ 2 callersFunctioncubic
(x)
ldm/modules/image_degradation/utils_image.py:700
↓ 2 callersMethoddecode
(self, text)
ldm/modules/encoders/modules.py:150
↓ 2 callersMethoddecode
(self, z)
ldm/models/autoencoder.py:332
↓ 2 callersMethoddelta_border
:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and
ldm/models/diffusion/ddpm.py:692
↓ 2 callersMethoddelta_border
:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and
ldm/models/diffusion/backup_ddpm.py:639
↓ 2 callersMethoddelta_border
:param h: height :param w: width :return: normalized distance to image border, wtith min distance = 0 at border and
ldm/models/diffusion/all_functions_ddpm.py:665
↓ 2 callersMethodema_scope
(self, context=None)
ldm/models/autoencoder.py:65
↓ 2 callersMethodema_scope
(self, context=None)
ldm/models/diffusion/ddpm.py:182
↓ 2 callersMethodema_scope
(self, context=None)
ldm/models/diffusion/backup_ddpm.py:182
↓ 2 callersMethodema_scope
(self, context=None)
ldm/models/diffusion/all_functions_ddpm.py:182
↓ 2 callersMethodencode_first_stage
(self, x)
ldm/models/diffusion/all_functions_ddpm.py:875
↓ 2 callersMethodevaluate_pr
Evaluate precision and recall efficiently. :param features_1: [N1 x D] feature vectors for reference batch. :param radii_1:
ldm/modules/evaluate/adm_evaluator.py:347
↓ 2 callersMethodfind_in_interval
(self, n)
ldm/lr_scheduler.py:52
↓ 2 callersFunctionflip_yz
(C2W)
dataloader/util_3dphoto.py:121
↓ 2 callersMethodforward_inner
(self, x, c, original_img=None, *args, **kwargs)
ldm/models/diffusion/ddpm.py:1028
↓ 2 callersMethodforward_inner
(self, x, c, original_img=None, *args, **kwargs)
ldm/models/diffusion/all_functions_ddpm.py:929
↓ 2 callersMethodfrechet_distance
Compute the Frechet distance between two sets of statistics.
ldm/modules/evaluate/adm_evaluator.py:93
↓ 2 callersMethodget_conditioning
(self, batch, k=None)
ldm/models/diffusion/classifier.py:133
↓ 2 callersFunctionget_data_from_str
(input_str,nprc = None)
ldm/modules/evaluate/torch_frechet_video_distance.py:119
↓ 2 callersMethodget_first_stage_encoding
(self, encoder_posterior)
ldm/models/diffusion/ddpm.py:663
↓ 2 callersMethodget_first_stage_encoding
(self, encoder_posterior)
ldm/models/diffusion/all_functions_ddpm.py:636
↓ 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/backup_ddpm.py:723
← previousnext →101–200 of 1,032, ranked by callers