MCPcopy Create free account

hub / github.com/SizheAn/PanoHead / functions

Functions563 in github.com/SizheAn/PanoHead

⨍ Functions 563◇ Types & classes 69↳ Endpoints 14
↓ 56 callersMethodappend
(self, x)
metrics/metric_utils.py:98
↓ 54 callersMethodmean
r"""Returns the mean of the scalars that were accumulated for the given statistic between the last two calls to `update()`, or NaN if
torch_utils/training_stats.py:190
↓ 47 callersFunctionkwarg
(tf_name, default=None, none=None)
legacy.py:116
↓ 41 callersMethodsynthesis
(self, ws, c, neural_rendering_resolution=None, update_emas=False, ws_bcg=None, cache_backbone=Fa
training/triplane.py:82
↓ 38 callersMethodmapping
(self, z, c, truncation_psi=1, truncation_cutoff=None, update_emas=False)
training/triplane.py:53
↓ 26 callersMethodsample
(horizontal_mean, vertical_mean, lookat_position, horizontal_stddev=0, vertical_stddev=0, radius=1, batch_size
camera_utils.py:69
↓ 19 callersMethodload
(pkl_file)
metrics/metric_utils.py:146
↓ 19 callersMethodsave
(self, pkl_file)
metrics/metric_utils.py:141
↓ 17 callersMethodupdate
(self, cur_items)
metrics/metric_utils.py:171
↓ 12 callersMethodbackward
(ctx, dy)
torch_utils/ops/bias_act.py:160
↓ 11 callersMethod__init__
(self, z_dim, # Input latent (Z) dimensionality. c_dim,
training/networks_stylegan2.py:534
↓ 11 callersMethodsample_mixed
(self, coordinates, directions, ws, truncation_psi=1, truncation_cutoff=None, update_emas=False, **synthesis_k
training/triplane.py:148
↓ 11 callersMethodupdate
(self, image)
gui_utils/gl_utils.py:181
↓ 9 callersFunctionsinc
(x)
metrics/equivariance.py:24
↓ 8 callersMethod_get_raw_labels
(self)
training/dataset.py:51
↓ 8 callersFunctionconvert_sdf_samples_to_ply
Convert sdf samples to .ply :param pytorch_3d_sdf_tensor: a torch.FloatTensor of shape (n,n,n) :voxel_grid_origin: a list of three floats
shape_utils.py:40
↓ 8 callersFunctionerror
(msg)
dataset_tool_seg.py:27
↓ 8 callersFunctionerror
(msg)
dataset_tool.py:31
↓ 8 callersFunctionfiltered_resizing
(image_orig_tensor, size, f, filter_mode='antialiased')
training/dual_discriminator.py:79
↓ 8 callersMethodsub
(self, tag=None, num_items=None, flush_interval=1000, rel_lo=0, rel_hi=1)
metrics/metric_utils.py:186
↓ 7 callersMethodclose
Flush, close possible files, and remove stdout/stderr mirroring.
dnnlib/util.py:102
↓ 7 callersFunctionmatrix
(*rows, device=None)
training/augment.py:50
↓ 7 callersMethodupdate
r"""Copies current values of the internal counters to the user-visible state and resets them for the next round. If `keep_previous=Tr
torch_utils/training_stats.py:149
↓ 6 callersFunctionFOV_to_intrinsics
Creates a 3x3 camera intrinsics matrix from the camera field of view, specified in degrees. Note the intrinsics are returned as normalized by
camera_utils.py:140
↓ 6 callersFunction_conv2d_wrapper
Wrapper for the underlying `conv2d()` and `conv_transpose2d()` implementations.
torch_utils/ops/conv2d_resample.py:31
↓ 6 callersFunction_parse_padding
(padding)
torch_utils/ops/upfirdn2d.py:46
↓ 6 callersFunction_parse_scaling
(scaling)
torch_utils/ops/upfirdn2d.py:37
↓ 6 callersFunctionsave_image_grid
(img, fname, drange, grid_size)
training/training_loop.py:71
↓ 6 callersMethodstd
r"""Returns the standard deviation of the scalars that were accumulated for the given statistic between the last two calls to `update(
torch_utils/training_stats.py:200
↓ 6 callersMethodwrite
Write text to stdout (and a file) and optionally flush.
dnnlib/util.py:80
↓ 5 callersMethod__init__
(self, z_dim, # Input latent (Z) dimensionality. c_dim,
training/networks_stylegan3.py:493
↓ 5 callersMethod__init__
(self, in_channels, # Number of input channels, 0 = first block. ou
training/superresolution.py:159
↓ 5 callersFunction_get_filter_size
(f)
torch_utils/ops/upfirdn2d.py:57
↓ 5 callersMethodget_label
(self, idx)
training/dataset.py:99
↓ 5 callersFunctioniterate_images
()
dataset_tool.py:86
↓ 5 callersFunctionmaybe_min
(a: int, b: Optional[int])
dataset_tool.py:51
↓ 5 callersFunctionscale2d_inv
(sx, sy, **kwargs)
training/augment.py:110
↓ 4 callersMethod__init__
(self, c_dim, # Conditioning label (C) dimensionality. img_resolution
training/dual_discriminator.py:101
↓ 4 callersFunction_conv2d_gradfix
(transpose, weight_shape, stride, padding, output_padding, dilation, groups)
torch_utils/ops/conv2d_gradfix.py:68
↓ 4 callersMethod_load_raw_image
(self, raw_idx)
training/dataset.py:71
↓ 4 callersFunction_tuple_of_ints
(xs, ndim)
torch_utils/ops/conv2d_gradfix.py:57
↓ 4 callersFunctioncull_clouds_mask
(denities, thresh)
training/volumetric_rendering/renderer.py:87
↓ 4 callersMethodflush
Flush written text to both stdout and a file, if open.
dnnlib/util.py:95
↓ 4 callersMethodget_all
(self)
metrics/metric_utils.py:127
↓ 4 callersFunctionget_texture_format
(dtype, channels)
gui_utils/gl_utils.py:78
↓ 4 callersFunctionlanczos_window
(x, a)
metrics/equivariance.py:29
↓ 4 callersMethodrun_model
(self, planes, decoder, sample_coordinates, sample_directions, options)
training/volumetric_rendering/renderer.py:198
↓ 3 callersMethod__init__
(self, name, # Name of the dataset. raw_shape, # Shape of the r
training/dataset.py:24
↓ 3 callersMethod_file_ext
(fname)
training/dataset.py:191
↓ 3 callersMethod_get_delta
r"""Returns the raw moments that were accumulated for the given statistic between the last two calls to `update()`, or zero if no scal
torch_utils/training_stats.py:172
↓ 3 callersFunction_unbroadcast
(x, shape)
torch_utils/ops/fma.py:51
↓ 3 callersMethodbind
(self)
gui_utils/gl_utils.py:175
↓ 3 callersFunctioncreate_cam2world_matrix
Takes in the direction the camera is pointing and the camera origin and returns a cam2world matrix. Works on batches of forward_vectors, orig
camera_utils.py:118
↓ 3 callersMethodend_frame
(self)
gui_utils/glfw_window.py:200
↓ 3 callersFunctionfile_ext
(name: Union[str, Path])
dataset_tool.py:58
↓ 3 callersFunctionget_obj_from_module
Traverses the object name and returns the last (rightmost) python object.
dnnlib/util.py:279
↓ 3 callersFunctionlogprint
(*args)
projector.py:39
↓ 3 callersFunctionlogprint
(*args)
projector_withseg.py:66
↓ 3 callersMethodmake_context_current
(self)
gui_utils/glfw_window.py:159
↓ 3 callersFunctionmatrix2angle
compute three Euler angles from a Rotation Matrix. Ref: http://www.gregslabaugh.net/publications/euler.pdf refined by: https://stackoverflow.com/
training/utils.py:24
↓ 3 callersFunctionnamed_params_and_buffers
(module)
torch_utils/misc.py:153
↓ 3 callersFunctionnorm_range
(t, value_range=(-1, 1))
gen_interpolation.py:71
↓ 3 callersFunctionprepare_texture_data
(image)
gui_utils/gl_utils.py:83
↓ 3 callersFunctionrotate2d_inv
(theta, **kwargs)
training/augment.py:113
↓ 3 callersFunctionrotation_matrix
(angle)
metrics/equivariance.py:33
↓ 3 callersMethodrun_D
(self, img, c, blur_sigma=0, blur_sigma_raw=0, update_emas=False)
training/loss.py:80
↓ 3 callersFunctionscale2d
(sx, sy, **kwargs)
training/augment.py:75
↓ 3 callersFunctiontranslate2d
(tx, ty, **kwargs)
training/augment.py:60
↓ 3 callersFunctiontranslate2d_inv
(tx, ty, **kwargs)
training/augment.py:107
↓ 3 callersFunctionupfirdn2d
r"""Pad, upsample, filter, and downsample a batch of 2D images. Performs the following sequence of operations for each channel: 1. Upsample
torch_utils/ops/upfirdn2d.py:120
↓ 2 callersFunctionP2sRt
decompositing camera matrix P. Args: P: (3, 4). Affine Camera Matrix. Returns: s: scale factor. R: (3, 3). rotation m
training/utils.py:4
↓ 2 callersMethod_attach_glfw_callbacks
(self)
gui_utils/glfw_window.py:220
↓ 2 callersFunction_collect_tf_params
(tf_net)
legacy.py:75
↓ 2 callersFunction_filtered_lrelu_cuda
Fast CUDA implementation of `filtered_lrelu()` using custom ops.
torch_utils/ops/filtered_lrelu.py:161
↓ 2 callersFunction_get_array_priv
( string: str, *, size: int = 32, max_width: Optional[int]=None, max_height: Optional[int]=Non
gui_utils/text_utils.py:47
↓ 2 callersFunction_get_filter_size
(f)
torch_utils/ops/filtered_lrelu.py:37
↓ 2 callersFunction_get_weight_shape
(w)
torch_utils/ops/conv2d_resample.py:23
↓ 2 callersMethod_get_zipfile
(self)
training/dataset.py:194
↓ 2 callersMethod_open_file
(self, fname)
training/dataset.py:200
↓ 2 callersFunction_parse_padding
(padding)
torch_utils/ops/filtered_lrelu.py:44
↓ 2 callersFunction_populate_module_params
(module, *patterns)
legacy.py:88
↓ 2 callersFunction_should_use_custom_op
(input)
torch_utils/ops/conv2d_gradfix.py:49
↓ 2 callersFunction_upfirdn2d_cuda
Fast CUDA implementation of `upfirdn2d()` using custom ops.
torch_utils/ops/upfirdn2d.py:219
↓ 2 callersMethodappend_torch
(self, x, num_gpus=1, rank=0)
metrics/metric_utils.py:115
↓ 2 callersMethodapply_delta_c
Input: z: latent code z c: latent code c Output: c_new: latent code c after adding the delta delta_c
training/triplane.py:59
↓ 2 callersMethodas_dict
r"""Returns the averages accumulated between the last two calls to `update()` as an `dnnlib.EasyDict`. The contents are as follows:
torch_utils/training_stats.py:214
↓ 2 callersMethodbind
(self)
gui_utils/gl_utils.py:292
↓ 2 callersFunctionbutton
(label, width=0, enabled=True)
gui_utils/imgui_utils.py:92
↓ 2 callersFunctioncalc_output_padding
(input_shape, output_shape)
torch_utils/ops/conv2d_gradfix.py:95
↓ 2 callersMethodclose
(self)
training/dataset.py:68
↓ 2 callersFunctioncompute_distances
(row_features, col_features, num_gpus, rank, col_batch_size)
metrics/precision_recall.py:21
↓ 2 callersFunctionconstruct_affine_bandlimit_filter
(mat, a=3, amax=16, aflt=64, up=4, cutoff_in=1, cutoff_out=1)
metrics/equivariance.py:104
↓ 2 callersFunctionconvert_mrc
(input_filename, output_filename, isosurface_level=1)
shape_utils.py:103
↓ 2 callersFunctionconvert_tf_generator
(tf_G)
legacy.py:109
↓ 2 callersMethoddesign_lowpass_filter
(numtaps, cutoff, width, fs, radial=False)
training/networks_stylegan3.py:366
↓ 2 callersFunctiondrag_previous_control
(enabled=True)
gui_utils/imgui_utils.py:139
↓ 2 callersFunctiondraw_shape
(vertices, *, mode=gl.GL_TRIANGLE_FAN, pos=0, size=1, color=1, alpha=1)
gui_utils/gl_utils.py:310
↓ 2 callersFunctionfile_ext
(name: Union[str, Path])
dataset_tool_seg.py:54
↓ 2 callersFunctiongen_interp_video
(G, mp4: str, seeds, pose_cond, shuffle_seed=None, w_frames=60*4, kind='cubic', grid_dims=(1,1), num_keyframes
gen_videos.py:69
↓ 2 callersFunctiongen_interp_video
(G, mp4: str, seeds, pose_cond, shuffle_seed=None, w_frames=60*4, kind='cubic', grid_dims=(1,1), num_keyframes
gen_videos_interp.py:69
next →1–100 of 563, ranked by callers