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
Functionblur
x: image, NxcxHxW k: kernel, Nx1xhxw
ldm/modules/image_degradation/bsrgan_light.py:128
Functionblur
x: image, NxcxHxW k: kernel, Nx1xhxw
ldm/modules/image_degradation/bsrgan.py:128
Methodbuild_from_config
(config)
annotator/zoe/zoedepth/models/zoedepth/zoedepth_v1.py:249
Methodbuild_from_config
(config)
annotator/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py:332
Functionbuild_model
Builds a model from a config. The model is specified by the model name and version in the config. The model is then constructed using the build_from_c
annotator/zoe/zoedepth/models/builder.py:28
Functioncalculate_psnr
(img1, img2, border=0)
ldm/modules/image_degradation/utils_image.py:621
Functioncalculate_ssim
calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255]
ldm/modules/image_degradation/utils_image.py:642
Methodcallback
(self, data)
annotator/zoe/zoedepth/models/base_models/midas_repo/ros/midas_cpp/scripts/listener_original.py:25
Methodcallback
(self, data)
annotator/zoe/zoedepth/models/base_models/midas_repo/ros/midas_cpp/scripts/listener.py:25
Functionchannel_convert
(in_c, tar_type, img_list)
ldm/modules/image_degradation/utils_image.py:597
Functionclassical_degradation
blur + downsampling Args: x: HxWxC image, [0, 1]/[0, 255] k: hxw, double sf: down-scale factor Return: downsa
ldm/modules/image_degradation/bsrgan_light.py:284
Functionclassical_degradation
blur + downsampling Args: x: HxWxC image, [0, 1]/[0, 255] k: hxw, double sf: down-scale factor Return: downsa
ldm/modules/image_degradation/bsrgan.py:284
Methodconfigure_optimizers
(self)
ldm/models/diffusion/classifier.py:220
Methodconvert_2d_to_3d_block
(block)
controlnet/unet_3d_condition.py:447
Methodconvert_2d_to_3d_block
(block)
controlnet/controlnet_3d.py:549
Functionconvnext_base
(pretrained=False, in_22k=False, **kwargs)
ldm/modules/diffusionmodules/convnext.py:178
Functionconvnext_large
(pretrained=False, in_22k=False, **kwargs)
ldm/modules/diffusionmodules/convnext.py:187
Functionconvnext_small
(pretrained=False,in_22k=False, **kwargs)
ldm/modules/diffusionmodules/convnext.py:169
Functionconvnext_tiny
(pretrained=False,in_22k=False, **kwargs)
ldm/modules/diffusionmodules/convnext.py:160
Functionconvnext_xlarge
(pretrained=False, in_22k=False, **kwargs)
ldm/modules/diffusionmodules/convnext.py:196
Methodcopy_to
(self, model)
ldm/modules/ema.py:46
Functioncount_parameters
(model, include_all=False)
annotator/zoe/zoedepth/utils/misc.py:155
Methodcreate_custom_forward
(module, return_dict=None)
controlnet/unet_3d_blocks.py:295
Methodcreate_custom_forward
(module)
controlnet/unet_3d_blocks.py:389
Methodcreate_custom_forward
(module, return_dict=None)
controlnet/unet_3d_blocks.py:505
Methodcreate_custom_forward
(module)
controlnet/unet_3d_blocks.py:592
Functioncreate_triangles
Reference: https://github.com/google-research/google-research/blob/e96197de06613f1b027d20328e06d69829fa5a89/infinite_nature/render_utils.py#L68
annotator/zoe/zoedepth/utils/geometry.py:75
Functioncrop_black_or_white_border
Crops the white and black border of the RGB and depth images. Args: rgb: RGB image, shape (H, W, 3). This image is used to determine the
annotator/zoe/zoedepth/data/preprocess.py:136
Methodcustom_forward
(*inputs)
controlnet/unet_3d_blocks.py:296
Methodcustom_forward
(*inputs)
controlnet/unet_3d_blocks.py:390
Methodcustom_forward
(*inputs)
controlnet/unet_3d_blocks.py:506
Methodcustom_forward
(*inputs)
controlnet/unet_3d_blocks.py:593
Methoddecode
(self, text)
ldm/modules/encoders/modules_backup.py:76
Methoddecode
(self, text)
ldm/modules/encoders/modules.py:78
Functiondegradation_bsrgan
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
ldm/modules/image_degradation/bsrgan_light.py:442
Functiondegradation_bsrgan
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
ldm/modules/image_degradation/bsrgan.py:438
Functiondegradation_bsrgan_plus
This is an extended degradation model by combining the degradation models of BSRGAN and Real-ESRGAN ---------- img: HXWXC, [0, 1], it
ldm/modules/image_degradation/bsrgan.py:617
Functiondegradation_bsrgan_variant
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
ldm/modules/image_degradation/bsrgan_light.py:534
Functiondegradation_bsrgan_variant
This is the degradation model of BSRGAN from the paper "Designing a Practical Degradation Model for Deep Blind Image Super-Resolution" --
ldm/modules/image_degradation/bsrgan.py:530
Functiondenormalize
Reverses the imagenet normalization applied to the input. Args: x (torch.Tensor - shape(N,3,H,W)): input tensor Returns: tor
annotator/zoe/zoedepth/utils/misc.py:60
Functiondepth_to_points
(depth, R=None, t=None)
annotator/zoe/zoedepth/utils/geometry.py:39
Functiondisabled_train
Overwrite model.train with this function to make sure train/eval mode does not change anymore.
ldm/models/diffusion/classifier.py:22
Functiondpsr_degradation
bicubic downsampling + blur Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam
ldm/modules/image_degradation/bsrgan_light.py:262
Functiondpsr_degradation
bicubic downsampling + blur Args: x: HxWxC image, [0, 1] k: hxw, double sf: down-scale factor Return: downsam
ldm/modules/image_degradation/bsrgan.py:262
Methodencode
(self, *args, **kwargs)
ldm/modules/encoders/modules_backup.py:16
Methodencode
(self, x)
ldm/modules/encoders/modules_backup.py:49
Methodencode
(self, text)
ldm/modules/encoders/modules_backup.py:70
Methodencode
(self, text)
ldm/modules/encoders/modules_backup.py:101
Methodencode
(self, x)
ldm/modules/encoders/modules_backup.py:134
Methodencode
(self, text)
ldm/modules/encoders/modules_backup.py:161
Methodencode
(self, text)
ldm/modules/encoders/modules_backup.py:189
Methodencode
(self, *args, **kwargs)
ldm/modules/encoders/modules.py:16
Methodencode
(self, x)
ldm/modules/encoders/modules.py:49
Methodencode
(self, text)
ldm/modules/encoders/modules.py:72
Methodencode
(self, x)
ldm/modules/encoders/modules.py:141
Methodencode
(self, text, return_pooler_output=False)
ldm/modules/encoders/modules.py:172
Methodencode
(self, text)
ldm/modules/encoders/modules.py:200
Functionexp_attractor
Exponential attractor: dc = exp(-alpha*|dx|^gamma) * dx , where dx = a - c, a = attractor point, c = bin center, dc = shift in bin centermmary for exp
annotator/zoe/zoedepth/models/layers/attractor.py:30
Methodfill_inf_from_mask
(self, sim, mask)
controlnet/attention.py:305
Methodfill_inf_from_mask
(self, sim, mask)
controlnet/attention.py:397
Methodfill_inf_from_mask
(self, sim, mask)
ldm/modules/attention.py:110
Methodfill_inf_from_mask
(self, sim, mask)
ldm/modules/attention.py:158
Methodfn_recursive_add_processors
(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor])
controlnet/controlnet.py:312
Methodfn_recursive_attn_processor
(name: str, module: torch.nn.Module, processor)
controlnet/controlnet.py:343
Methodfn_recursive_retrieve_slicable_dims
(module: torch.nn.Module)
controlnet/unet_3d_condition.py:225
Methodfn_recursive_retrieve_slicable_dims
(module: torch.nn.Module)
controlnet/controlnet.py:371
Methodfn_recursive_retrieve_slicable_dims
(module: torch.nn.Module)
controlnet/controlnet_3d.py:347
Methodfn_recursive_set_attention_slice
(module: torch.nn.Module, slice_size: List[int])
controlnet/unet_3d_condition.py:265
Methodfn_recursive_set_attention_slice
(module: torch.nn.Module, slice_size: List[int])
controlnet/controlnet.py:409
Methodfn_recursive_set_attention_slice
(module: torch.nn.Module, slice_size: List[int])
controlnet/controlnet_3d.py:387
Methodforward
( self, sample: torch.FloatTensor, timestep: Union[torch.Tensor, float, int],
controlnet/unet_3d_condition.py:283
Methodforward
(self, hidden_states, encoder_hidden_states=None, attention_mask=None, **cross_attention_kwargs)
controlnet/attention_processor.py:187
Methodforward
(self, hidden_states)
controlnet/attention_processor.py:327
Methodforward
(self, hidden_states, encoder_hidden_states=None, attention_mask=None)
controlnet/cross_attention_old.py:104
Methodforward
(self, conditioning)
controlnet/controlnet.py:63
Methodforward
( self, sample: torch.FloatTensor, timestep: Union[torch.Tensor, float, int],
controlnet/controlnet.py:424
Methodforward
( self, hidden_states, encoder_hidden_states=None, timestep=None, return_dict: bool = True )
controlnet/attention.py:88
Methodforward
( self, hidden_states, encoder_hidden_states=None, timestep=None, atte
controlnet/attention.py:231
Methodforward
(self, x, key, value, mask=None)
controlnet/attention.py:314
Methodforward
(self, hidden_states, attention_mask=None, clip_length=None)
controlnet/attention.py:338
Methodforward
(self, x, key, value, mask=None)
controlnet/attention.py:405
Methodforward
(self, conditioning)
controlnet/controlnet_3d.py:73
Methodforward
( self, sample: torch.FloatTensor, timestep: Union[torch.Tensor, float, int],
controlnet/controlnet_3d.py:405
Methodforward
( self, sample: torch.FloatTensor, timestep: Union[torch.Tensor, float, int],
controlnet/controlnet_3d.py:607
Methodforward
(self, hidden_states, temb=None, encoder_hidden_states=None, attention_mask=None)
controlnet/unet_3d_blocks.py:197
Methodforward
(self, hidden_states, temb=None, encoder_hidden_states=None, attention_mask=None)
controlnet/unet_3d_blocks.py:288
Methodforward
(self, hidden_states, temb=None)
controlnet/unet_3d_blocks.py:383
Methodforward
( self, hidden_states, res_hidden_states_tuple, temb=None, encoder_hid
controlnet/unet_3d_blocks.py:487
Methodforward
(self, hidden_states, res_hidden_states_tuple, temb=None, upsample_size=None)
controlnet/unet_3d_blocks.py:583
Methodforward
(self, x)
controlnet/resnet.py:36
Methodforward
(self, hidden_states, output_size=None)
controlnet/resnet.py:96
Methodforward
(self, hidden_states)
controlnet/resnet.py:174
Methodforward
(self, input_tensor, temb)
controlnet/resnet.py:290
Methodforward
(self, input, target, mask=None, interpolate=True, return_interpolated=False)
annotator/zoe/zoedepth/trainers/loss.py:49
Methodforward
(self, input, target, mask=None, interpolate=True, return_interpolated=False)
annotator/zoe/zoedepth/trainers/loss.py:116
Methodforward
(self, input, target, mask=None, interpolate=True, return_interpolated=False)
annotator/zoe/zoedepth/trainers/loss.py:221
Methodforward
(self, prediction, target, mask, interpolate=True, return_interpolated=False)
annotator/zoe/zoedepth/trainers/loss.py:286
Methodforward
(self, x, *args, **kwargs)
annotator/zoe/zoedepth/models/depth_model.py:44
Methodforward
(self, x, denorm=False, return_rel_depth=False)
annotator/zoe/zoedepth/models/base_models/midas.py:259
Methodforward
Forward pass. Args: x (tensor): input data (image) Returns: tensor: depth
annotator/zoe/zoedepth/models/base_models/midas_repo/midas/midas_net_custom.py:73
← previousnext →701–800 of 1,051, ranked by callers