MCPcopy Create free account

hub / github.com/thygate/stable-diffusion-webui-depthmap-script / functions

Functions1,036 in github.com/thygate/stable-diffusion-webui-depthmap-script

⨍ Functions 1,036◇ Types & classes 199↳ Endpoints 4
↓ 2 callersMethodrotate_image
(self, image, angle, flag=Image.BILINEAR)
dzoedepth/data/data_mono.py:440
↓ 2 callersFunctionrun_3dphoto_videos
(mesh_fi, basename, outpath, num_frames, fps, crop_border, traj_types, x_shift_range, y
src/core.py:513
↓ 2 callersMethodsave_networks
Save all the networks to the disk. Parameters: epoch (int) -- current epoch; used in the file name '%s_net_%s.pth' % (epoch, name
pix2pix/models/base_model.py:144
↓ 2 callersMethodset_input
Unpack input data from the dataloader and perform necessary pre-processing steps. Parameters: input (dict): includes the data its
pix2pix/models/base_model.py:60
↓ 2 callersMethodset_input_train
(self, input)
pix2pix/models/pix2pix4depth_model.py:80
↓ 2 callersMethodset_requires_grad
Set requies_grad=Fasle for all the networks to avoid unnecessary computations Parameters: nets (network list) -- a list of netwo
pix2pix/models/base_model.py:219
↓ 2 callersMethodset_updated_estimate
(self, est)
src/depthmap_generation.py:585
↓ 2 callersMethodsetup
Load and print networks; create schedulers Parameters: opt (Option class) -- stores all the experiment flags; needs to be a subcl
pix2pix/models/base_model.py:78
↓ 2 callersMethodshould_early_stop
(self)
dzoedepth/trainers/base_trainer.py:138
↓ 2 callersFunctionsingleestimate
(img, msize, model, net_type)
src/depthmap_generation.py:1053
↓ 2 callersFunctionsparse_bilateral_filtering
config: - filter_size
inpaint/bilateral_filtering.py:4
↓ 2 callersFunctionto_base64_PIL
(encoding: str)
scripts/depthmap_api.py:38
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/vkitti.py:52
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/vkitti2.py:53
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/diode.py:51
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/data_mono.py:543
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/diml_outdoor_test.py:48
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/sun_rgbd_loader.py:48
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/hypersim.py:68
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/ddad.py:51
↓ 2 callersMethodto_tensor
(self, pic)
dzoedepth/data/diml_indoor_test.py:51
↓ 2 callersMethodunfreeze
(self)
dzoedepth/models/base_models/midas.py:246
↓ 2 callersMethodvalidate
(self)
dzoedepth/trainers/base_trainer.py:259
↓ 2 callersFunctionvoxel_to_point
(x, z, nearest=False)
lib/spvcnn_utils.py:65
↓ 2 callersFunctionwrite_mesh
(image, depth, int_mtx, ply_name, config,
inpaint/mesh.py:1828
↓ 1 callersFunctionDINOv2
(model_name)
ddepth_anything_v2/depth_anything_v2/dinov2.py:398
↓ 1 callersFunctionDINOv2
(model_name)
ddepth_anything_v2/metric_depth/depth_anything_v2/dinov2.py:398
↓ 1 callersFunction__crop
(img, pos, size)
pix2pix/data/base_dataset.py:135
↓ 1 callersMethod__encode_empty_text
Encode text embedding for empty prompt
dmarigold/marigold/marigold_pipeline.py:238
↓ 1 callersFunction__flip
(img, flip)
pix2pix/data/base_dataset.py:144
↓ 1 callersMethod__getattr__
(self, item)
src/core.py:79
↓ 1 callersMethod__init__
Init. Args: width (int): desired output width height (int): desired output height resize_target (bool, opt
dzoedepth/models/base_models/midas.py:54
↓ 1 callersMethod__init__
Compute log binomial distribution for n_classes Args: n_classes (int, optional): number of output classes. Defaults to 256.
dzoedepth/models/layers/dist_layers.py:37
↓ 1 callersMethod__init__
Attractor layer for bin centers. Bin centers are bounded on the interval (min_depth, max_depth)
dzoedepth/models/layers/attractor.py:61
↓ 1 callersMethod__init__
(self, encoder)
lib/multi_depth_model_woauxi.py:24
↓ 1 callersMethod__init__
( self, head, features=256, backbone="vitb_rn50_384", readout="project
dmidas/dpt_depth.py:32
↓ 1 callersMethod__init__
Init. Args: features (int): number of features
ddepth_anything_v2/depth_anything_v2/util/blocks.py:33
↓ 1 callersMethod__init__
( self, in_features: int, hidden_features: Optional[int] = None, out_features:
ddepth_anything_v2/depth_anything_v2/dinov2_layers/swiglu_ffn.py:14
↓ 1 callersMethod__init__
Init. Args: features (int): number of features
ddepth_anything_v2/metric_depth/depth_anything_v2/util/blocks.py:33
↓ 1 callersMethod__init__
( self, in_features: int, hidden_features: Optional[int] = None, out_features:
ddepth_anything_v2/metric_depth/depth_anything_v2/dinov2_layers/swiglu_ffn.py:14
↓ 1 callersFunction__make_power_2
(img, base, method=Image.BICUBIC)
pix2pix/data/base_dataset.py:115
↓ 1 callersMethod__patch_instance_norm_state_dict
Fix InstanceNorm checkpoints incompatibility (prior to 0.4)
pix2pix/models/base_model.py:162
↓ 1 callersFunction__print_size_warning
Print warning information about image size(only print once)
pix2pix/data/base_dataset.py:150
↓ 1 callersFunction__scale_width
(img, target_size, crop_size, method=Image.BICUBIC)
pix2pix/data/base_dataset.py:126
↓ 1 callersMethod_create_ord_label
(self, gt)
dzoedepth/trainers/loss.py:144
↓ 1 callersMethod_download_data
(self, dataset_url, save_path)
pix2pix/util/get_data.py:56
↓ 1 callersMethod_forward_impl
(self, x)
lib/Resnext_torch.py:196
↓ 1 callersMethod_get_intermediate_layers_chunked
(self, x, n=1)
ddepth_anything_v2/depth_anything_v2/dinov2.py:283
↓ 1 callersMethod_get_intermediate_layers_chunked
(self, x, n=1)
ddepth_anything_v2/metric_depth/depth_anything_v2/dinov2.py:283
↓ 1 callersMethod_get_intermediate_layers_not_chunked
(self, x, n=1)
ddepth_anything_v2/depth_anything_v2/dinov2.py:271
↓ 1 callersMethod_get_intermediate_layers_not_chunked
(self, x, n=1)
ddepth_anything_v2/metric_depth/depth_anything_v2/dinov2.py:271
↓ 1 callersMethod_get_options
(r)
pix2pix/util/get_data.py:40
↓ 1 callersMethod_infer
Inference interface for the model Args: x (torch.Tensor): input tensor of shape (b, c, h, w) Returns:
dzoedepth/models/depth_model.py:47
↓ 1 callersMethod_init_params
(self)
lib/network_auxi.py:34
↓ 1 callersMethod_initialize_weights
(self)
dmidas/backbones/next_vit.py:407
↓ 1 callersFunction_is_numpy_image
(img)
dzoedepth/data/data_mono.py:60
↓ 1 callersFunction_is_pil_image
(img)
dzoedepth/data/data_mono.py:56
↓ 1 callersFunction_make_efficientnet_backbone
(effnet)
dmidas/blocks.py:179
↓ 1 callersFunction_make_levit_backbone
( model, hooks=[3, 11, 21], patch_grid=[14, 14] )
dmidas/backbones/levit.py:23
↓ 1 callersFunction_make_next_vit_backbone
( model, hooks=[2, 6, 36, 39], )
dmidas/backbones/next_vit.py:459
↓ 1 callersFunction_make_pretrained_beitb16_384
(pretrained, use_readout="ignore", hooks=None)
dmidas/backbones/beit.py:189
↓ 1 callersFunction_make_pretrained_beitl16_384
(pretrained, use_readout="ignore", hooks=None)
dmidas/backbones/beit.py:176
↓ 1 callersFunction_make_pretrained_beitl16_512
(pretrained, use_readout="ignore", hooks=None)
dmidas/backbones/beit.py:159
↓ 1 callersFunction_make_pretrained_efficientnet_lite3
(use_pretrained, exportable=False)
dmidas/blocks.py:169
↓ 1 callersFunction_make_pretrained_levit_384
(pretrained, hooks=None)
dmidas/backbones/levit.py:99
↓ 1 callersFunction_make_pretrained_next_vit_large_6m
(hooks=None)
dmidas/backbones/next_vit.py:476
↓ 1 callersFunction_make_pretrained_resnext101_wsl
(use_pretrained)
dmidas/blocks.py:205
↓ 1 callersFunction_make_pretrained_swin2b24_384
(pretrained, hooks=None)
dmidas/backbones/swin2.py:16
↓ 1 callersFunction_make_pretrained_swin2l24_384
(pretrained, hooks=None)
dmidas/backbones/swin2.py:6
↓ 1 callersFunction_make_pretrained_swin2t16_256
(pretrained, hooks=None)
dmidas/backbones/swin2.py:26
↓ 1 callersFunction_make_pretrained_swinl12_384
(pretrained, hooks=None)
dmidas/backbones/swin.py:6
↓ 1 callersFunction_make_pretrained_vitb16_384
(pretrained, use_readout="ignore", hooks=None)
dmidas/backbones/vit.py:111
↓ 1 callersFunction_make_pretrained_vitb_rn50_384
( pretrained, use_readout="ignore", hooks=None, use_vit_only=False )
dmidas/backbones/vit.py:208
↓ 1 callersFunction_make_pretrained_vitl16_384
(pretrained, use_readout="ignore", hooks=None)
dmidas/backbones/vit.py:98
↓ 1 callersFunction_make_resnet_backbone
(resnet)
dmidas/blocks.py:192
↓ 1 callersFunction_make_scratch
(in_shape, out_shape, groups=1, expand=False)
ddepth_anything_v2/depth_anything_v2/util/blocks.py:4
↓ 1 callersFunction_make_scratch
(in_shape, out_shape, groups=1, expand=False)
ddepth_anything_v2/metric_depth/depth_anything_v2/util/blocks.py:4
↓ 1 callersFunction_make_vit_b_rn50_backbone
( model, features=[256, 512, 768, 768], size=[384, 384], hooks=[0, 1, 8, 11], vit_features
dmidas/backbones/vit.py:120
↓ 1 callersMethod_present_options
(self)
pix2pix/util/get_data.py:46
↓ 1 callersFunctionacc_shape
(i)
inpaint/bilateral_filtering.py:208
↓ 1 callersFunctionadaptiveselection
(integral_grad, patch_bound_list, gf, factor)
src/depthmap_generation.py:1119
↓ 1 callersMethodadd_border
(self, input, channel_pad_1=None)
inpaint/networks.py:285
↓ 1 callersFunctionadd_residual
(x, brange, residual, residual_scale_factor, scaling_vector=None)
ddepth_anything_v2/depth_anything_v2/dinov2_layers/block.py:142
↓ 1 callersFunctionadd_residual
(x, brange, residual, residual_scale_factor, scaling_vector=None)
ddepth_anything_v2/metric_depth/depth_anything_v2/dinov2_layers/block.py:142
↓ 1 callersFunctionapplyGridpatch
(blsize, stride, img, box)
src/depthmap_generation.py:1102
↓ 1 callersFunctionapply_min_size
Rezise the sample to ensure the given size. Keeps aspect ratio. Args: sample (dict): sample size (tuple): image size Returns
dzoedepth/data/transforms.py:55
↓ 1 callersFunctionapply_stereo_divergence_naive
( original_image, normalized_depth, divergence_px: float, separation_px: float, stereo_offset_exponent
src/stereoimage_generation.py:96
↓ 1 callersFunctionapply_stereo_divergence_polylines
( original_image, normalized_depth, divergence_px: float, separation_px: float, stereo_offset_exponent
src/stereoimage_generation.py:163
↓ 1 callersMethodattach_hooks
(self, midas)
dzoedepth/models/base_models/midas.py:297
↓ 1 callersMethodaugment_image
(self, image)
dzoedepth/data/data_mono.py:488
↓ 1 callersMethodbackward_D
Calculate GAN loss for the discriminator
pix2pix/models/pix2pix4depth_model.py:118
↓ 1 callersMethodbackward_G
Calculate GAN and L1 loss for the generator
pix2pix/models/pix2pix4depth_model.py:132
↓ 1 callersFunctionbilateral_filter
(depth, config, discontinuity_map=None, HR=False, mask=None, window_size=False)
inpaint/bilateral_filtering.py:105
↓ 1 callersMethodbuild
(midas_model_type="DPT_BEiT_L_384", train_midas=False, use_pretrained_midas=True, fetch_features=False, freeze
dzoedepth/models/base_models/midas.py:333
↓ 1 callersMethodbuild
(midas_model_type="DPT_BEiT_L_384", pretrained_resource=None, use_pretrained_midas=False, train_midas=False, f
dzoedepth/models/zoedepth/zoedepth_v1.py:239
↓ 1 callersMethodbuild
(midas_model_type="DPT_BEiT_L_384", pretrained_resource=None, use_pretrained_midas=False, train_midas=False, f
dzoedepth/models/zoedepth_nk/zoedepth_nk_v1.py:322
↓ 1 callersFunctionbuild_connection
(mesh, cur_node, dst_node)
inpaint/mesh_tools.py:801
↓ 1 callersMethodbuild_conv_block
Construct a convolutional block. Parameters: dim (int) -- the number of channels in the conv layer. padding
pix2pix/models/networks.py:398
↓ 1 callersMethodbuild_from_config
(config)
dzoedepth/models/base_models/midas.py:352
↓ 1 callersFunctioncalculate_fov
(mesh)
inpaint/mesh.py:112
← previousnext →201–300 of 1,036, ranked by callers