MCPcopy Create free account

hub / github.com/Ground-A-Video/Ground-A-Video / functions

Functions1,051 in github.com/Ground-A-Video/Ground-A-Video

⨍ Functions 1,051◇ Types & classes 244
Methodforward
(self, text, return_offset_mapping=False)
ldm/modules/encoders/modules.py:95
Methodforward
(self,x)
ldm/modules/encoders/modules.py:132
Methodforward
(self, text, return_pooler_output=False)
ldm/modules/encoders/modules.py:159
Methodforward
(self, text)
ldm/modules/encoders/modules.py:193
Methodforward
(self, x)
ldm/modules/encoders/modules.py:237
Methodforward
(self, codebook_loss, inputs, reconstructions, optimizer_idx, global_step, last_layer=None, co
ldm/modules/losses/vqperceptual.py:98
Methodforward
(self, inputs, reconstructions, posteriors, optimizer_idx, global_step, last_layer=None, cond=
ldm/modules/losses/contperceptual.py:45
Methodforward
(self, x_noisy, t, *args, **kwargs)
ldm/models/diffusion/classifier.py:120
Functionforward_beit
(pretrained, x)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/beit.py:14
Functionforward_flex
(self, x)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py:33
Functionforward_levit
(pretrained, x)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/levit.py:9
Functionforward_next_vit
(pretrained, x)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/next_vit.py:11
Functionforward_swin
(pretrained, x)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/swin_common.py:9
Functionforward_vit
(pretrained, x)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py:12
Methodfreeze
(self)
ldm/modules/encoders/modules_backup.py:177
Methodfreeze
(self)
ldm/modules/encoders/modules.py:188
Methodfreeze_all_confs
Freezes all the parameters of all the ModuleDicts children
annotator/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py:311
Methodfreeze_conf
Freezes all the parameters of all the ModuleDicts children that are exclusively used for the given bin configuration
annotator/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py:297
Methodfrom_2d_model
(cls, model_path)
controlnet/unet_3d_condition.py:430
Methodfrom_unet
r""" Instantiate Controlnet class from UNet2DConditionModel. Parameters: unet (`UNet2DConditionModel`): UN
controlnet/controlnet.py:249
Methodfrom_unet
r""" Instantiate Controlnet class from UNet2DConditionModel. Parameters: unet (`UNet2DConditionModel`): UN
controlnet/controlnet_3d.py:278
Methodfuse
(self)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/levit.py:73
Functionfuse_model
(m)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/midas_net_custom.py:109
Functiongen_kernel
# modified version of https://github.com/assafshocher/BlindSR_dataset_generator # Kai Zhang # min_var = 0.175 * sf # variance of the gau
ldm/modules/image_degradation/bsrgan_light.py:145
Functiongen_kernel
# modified version of https://github.com/assafshocher/BlindSR_dataset_generator # Kai Zhang # min_var = 0.175 * sf # variance of the gau
ldm/modules/image_degradation/bsrgan.py:145
Methodget_base
(self)
ldm/data/imagenet.py:390
Methodget_last_layer
(self)
ldm/modules/diffusionmodules/model.py:364
Methodget_lr_params
Learning rate configuration for different layers of the model Args: lr (float) : Base learning rate Returns:
annotator/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py:245
Methodget_null_input
Guidance for training (drop) or inference, please define the null input for the grounding tokenizer
grounding_input/text_image_grounding_tokinzer_input.py:39
Methodget_rel_pos_params
(self)
annotator/zoe/zoedepth/models/base_models/midas.py:279
Functionget_trainer
Builds and returns a trainer based on the config. Args: config (dict): the config dict (typically constructed using utils.config.get_conf
annotator/zoe/zoedepth/trainers/builder.py:28
Functiongroup_by_key_prefix
(prefix, d)
ldm/modules/x_transformer.py:106
Functionhinge_d_loss_with_exemplar_weights
(logits_real, logits_fake, weights)
ldm/modules/losses/vqperceptual.py:11
Functionhook
(model, input, output)
annotator/zoe/zoedepth/models/base_models/midas.py:46
Functionhook
(model, input, output)
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/utils.py:57
MethodimageCb
annotator/zoe/zoedepth/models/base_models/midas_repo/ros/midas_cpp/src/main.cpp:170
Functionimg2mask
(img, H, W, low=10, high=90)
annotator/util.py:84
Functionimresize
(img, scale, antialiasing=True)
ldm/modules/image_degradation/utils_image.py:766
Functionimresize_np
(img, scale, antialiasing=True)
ldm/modules/image_degradation/utils_image.py:839
Functionimsave
(img, img_path)
ldm/modules/image_degradation/utils_image.py:203
Functionimshow
(x, title=None, cbar=False, figsize=None)
ldm/modules/image_degradation/utils_image.py:37
Functionimwrite
(img, img_path)
ldm/modules/image_degradation/utils_image.py:209
Methodinfer_pil
Inference interface for the model for PIL image Args: pil_img (PIL.Image.Image): input PIL image pad_input (b
annotator/zoe/zoedepth/models/depth_model.py:131
Functioninit_
(tensor)
ldm/modules/attention.py:30
Functioninner
(*args, **kwargs)
ldm/modules/x_transformer.py:65
Functioninv_attractor
Inverse attractor: dc = dx / (1 + alpha*dx^gamma), where dx = a - c, a = attractor point, c = bin center, dc = shift in bin center This is the def
annotator/zoe/zoedepth/models/layers/attractor.py:45
Functionisimage
(x)
ldm/util.py:40
Methoditers_per_epoch
(self)
annotator/zoe/zoedepth/trainers/base_trainer.py:131
Functionl1
(x, y)
ldm/modules/losses/vqperceptual.py:35
Functionl2
(x, y)
ldm/modules/losses/vqperceptual.py:39
Methodload_2d_state_dict
(self, state_dict, **kwargs)
ldm/modules/diffusionmodules/openaimodel.py:467
Methodload_2d_state_dict
(self, state_dict, **kwargs)
ldm/modules/diffusionmodules/openaimodel3d.py:494
Methodload_ckpt
(self, checkpoint_dir="./checkpoints", ckpt_type="best")
annotator/zoe/zoedepth/trainers/base_trainer.py:71
Methodlog_bar_plot
(self, title, labels, values)
annotator/zoe/zoedepth/trainers/base_trainer.py:319
Methodlog_images
(self, batch, N=8, *args, **kwargs)
ldm/models/diffusion/classifier.py:238
Methodlog_line_plot
(self, data)
annotator/zoe/zoedepth/trainers/base_trainer.py:310
Functionmain
annotator/zoe/zoedepth/models/base_models/midas_repo/ros/midas_cpp/src/main.cpp:279
Functionmake_noise_disk
(H, W, C, F)
annotator/util.py:61
Functionmax_neg_value
(t)
ldm/modules/attention.py:26
Functionmean_flat
https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/nn.py#L86 Take the mean over all no
ldm/util.py:56
Functionmean_flat
Take the mean over all non-batch dimensions.
ldm/modules/diffusionmodules/util.py:201
Functionmin_max_norm
(x)
annotator/util.py:72
Functionmkdir_and_rename
(path)
ldm/modules/image_degradation/utils_image.py:166
Functionmkdirs
(paths)
ldm/modules/image_degradation/utils_image.py:158
Functionmodcrop
(img_in, scale)
ldm/modules/image_degradation/utils_image.py:494
Functionmodcrop_np
Args: img: numpy image, WxH or WxHxC sf: scale factor Return: cropped image
ldm/modules/image_degradation/bsrgan_light.py:29
Functionmodcrop_np
Args: img: numpy image, WxH or WxHxC sf: scale factor Return: cropped image
ldm/modules/image_degradation/bsrgan.py:29
Methodmode
(self)
ldm/modules/distributions/distributions.py:9
Methodmode
(self)
ldm/modules/distributions/distributions.py:61
Methodnll
(self, sample, dims=[1,2,3])
ldm/modules/distributions/distributions.py:53
Functionnms
(x, t, s)
annotator/util.py:43
Functionnoise_like
(shape, device, repeat=False)
ldm/modules/diffusionmodules/util.py:281
Functionnormal_kl
source: https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/losses.py#L12 Compute the K
ldm/modules/distributions/distributions.py:65
Methodon_train_epoch_start
(self)
ldm/models/diffusion/classifier.py:157
Methodon_validation_start
(self)
ldm/models/diffusion/classifier.py:206
Methodopen
(self, fpath)
annotator/zoe/zoedepth/data/data_mono.py:254
Functionparallelize
(config, model, find_unused_parameters=True)
annotator/zoe/zoedepth/utils/misc.py:251
Functionparse_unknown
(unknown_args)
annotator/zoe/zoedepth/utils/arg_utils.py:22
Functionpatch_embed_forward
Modification of timm.models.layers.patch_embed.py: PatchEmbed.forward to support arbitrary window sizes.
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/beit.py:18
Functionpick_and_pop
(keys, d)
ldm/modules/x_transformer.py:88
Functionpil_to_batched_tensor
(img)
annotator/zoe/zoedepth/utils/misc.py:355
Methodprepare
batch should be the output from dataset. Please define here how to process the batch and prepare the input only for the grou
grounding_input/text_image_grounding_tokinzer_input.py:10
Functionprintc
(text, color)
annotator/zoe/zoedepth/utils/misc.py:337
Functionread_image
Read image and output RGB image (0-1). Args: path (str): path to file Returns: array: RGB image (0-1)
annotator/zoe/zoedepth/models/base_models/midas_repo/utils.py:98
Functionread_image
Read image and output RGB image (0-1). Args: path (str): path to file Returns: array: RGB image (0-1)
annotator/zoe/zoedepth/models/base_models/midas_repo/tf/utils.py:43
Functionread_img
(path)
ldm/modules/image_degradation/utils_image.py:220
Functionread_pfm
Read pfm file. Args: path (str): path to file Returns: tuple: (data, scale)
annotator/zoe/zoedepth/models/base_models/midas_repo/utils.py:10
Functionresize_depth
Resize depth map and bring to CPU (numpy). Args: depth (tensor): depth width (int): image width height (int): image heigh
annotator/zoe/zoedepth/models/base_models/midas_repo/utils.py:147
Functionresize_image
(input_image, resolution)
annotator/util.py:30
Functionresize_image
Resize image and make it fit for network. Args: img (array): image Returns: tensor: data ready for network
annotator/zoe/zoedepth/models/base_models/midas_repo/utils.py:117
Methodresize_to_target
(self, prediction, target)
annotator/zoe/zoedepth/trainers/base_trainer.py:64
Functionresnet101
r"""ResNet-101 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. Args: pretrained
ldm/modules/diffusionmodules/resnet.py:317
Functionresnet152
r"""ResNet-152 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. Args: pretrained
ldm/modules/diffusionmodules/resnet.py:328
Functionresnet18
r"""ResNet-18 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. Args: pretrained (
ldm/modules/diffusionmodules/resnet.py:284
Functionresnet34
r"""ResNet-34 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. Args: pretrained (
ldm/modules/diffusionmodules/resnet.py:295
Functionresnet50
r"""ResNet-50 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_. Args: pretrained (
ldm/modules/diffusionmodules/resnet.py:306
Methodrestore
Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the
ldm/modules/ema.py:64
Methodrestore_first_conv_from_GLIGEN
(self)
ldm/modules/diffusionmodules/openaimodel.py:416
Methodrestore_first_conv_from_GLIGEN
(self)
ldm/modules/diffusionmodules/openaimodel3d.py:428
Methodrestore_first_conv_from_SD
(self)
ldm/modules/diffusionmodules/openaimodel3d.py:405
← previousnext →901–1,000 of 1,051, ranked by callers