MCPcopy Create free account

hub / github.com/XingangPan/DragGAN / functions

Functions1,199 in github.com/XingangPan/DragGAN

Functionon_click_clear_points
Function to handle clear all control points 1. clear global_state['points'] (clear_state) 2. re-init network 2. re-draw image
visualizer_drag_gradio.py:829
Functionon_click_enable_draw
Function to start add mask mode. 1. Preprocess mask info from last state 2. Change editing state to add_mask 3. Set curr image
visualizer_drag_gradio.py:731
Functionon_click_image
This function only support click for point selection
visualizer_drag_gradio.py:789
Functionon_click_latent_space
Function to reset latent space to optimize. NOTE: this function we reset the image and all controls 1. Set latent-space to global_stat
visualizer_drag_gradio.py:404
Functionon_click_remove_draw
Function to start remove mask mode. 1. Preprocess mask info from last state 2. Change editing state to remove_mask 3. Set curr
visualizer_drag_gradio.py:746
Functionon_click_remove_point
(global_state)
visualizer_drag_gradio.py:695
Functionon_click_reset_image
Reset image to the original one and clear all states 1. Re-init images 2. Clear all states
visualizer_drag_gradio.py:368
Functionon_click_reset_mask
(global_state)
visualizer_drag_gradio.py:710
Functionon_click_show_mask
Function to control whether show mask on image.
visualizer_drag_gradio.py:849
Functionon_click_start
(global_state, image)
visualizer_drag_gradio.py:446
Functionon_click_stop
Function to handle stop button is clicked. 1. send a stop signal by set global_state["temporal_params"]["stop"] as True 2. Disable Sto
visualizer_drag_gradio.py:672
Functionopen_url
Download the given URL and return a binary-mode file object to access the data.
stylegan_human/dnnlib/util.py:384
Functionopen_url
Download the given URL and return a binary-mode file object to access the data.
dnnlib/util.py:396
FunctionpadRightDownCorner
(img, stride, padValue)
stylegan_human/openpose/src/util.py:12
Methodparams
(self)
stylegan_human/PP_HumanSeg/deploy/infer.py:54
Functionparams_and_buffers
(module)
torch_utils/misc.py:147
Functionparams_and_buffers
(module)
stylegan_human/torch_utils/misc.py:147
Functionparse_comma_separated_list
(s)
stylegan_human/training_scripts/sg3/train.py:120
Functionparse_range
Parse a comma separated list of numbers or ranges and return a list of ints. Example: '1,2,5-10' returns [1, 2, 5, 6, 7]
gen_images.py:25
Functionparse_vec2
Parse a floating point 2-vector of syntax 'a,b'. Example: '0,1' returns (0,1)
gen_images.py:43
Functionplot_image
(img)
stylegan_human/utils/log_utils.py:34
Functionplot_image_from_w
(w, G)
stylegan_human/utils/log_utils.py:27
Functionpopup_button
(label, width=0, enabled=True)
gui_utils/imgui_utils.py:112
Functionpost_hook
(mod, _inputs, outputs)
torch_utils/misc.py:206
Functionpost_hook
(mod, _inputs, outputs)
stylegan_human/torch_utils/misc.py:204
Functionpre_hook
(_mod, _inputs)
torch_utils/misc.py:204
Functionpre_hook
(_mod, _inputs)
stylegan_human/torch_utils/misc.py:202
Methodpreprocess
(self, x)
gradio_utils/utils.py:19
Methodprint_layers
Print a summary table of the network structure.
stylegan_human/dnnlib/tflib/network.py:508
Functionprint_module_summary
(module, inputs, max_nesting=3, skip_redundant=True)
torch_utils/misc.py:196
Functionprint_module_summary
(module, inputs, max_nesting=3, skip_redundant=True)
stylegan_human/torch_utils/misc.py:194
Functionprofiled_function
(fn)
torch_utils/misc.py:100
Functionprofiled_function
(fn)
stylegan_human/torch_utils/misc.py:100
Functionproject
( G, target: torch.Tensor, # [C,H,W] and dynamic range [0,255], W & H must match G output res
stylegan_human/pti/training/projectors/w_plus_projector.py:22
Functionproject
( G, target: torch.Tensor, # [C,H,W] and dynamic range [0,255], W & H must match G output res
stylegan_human/pti/training/projectors/w_projector.py:22
Methodquery
Return w's from the pool. Parameters: ws: the latest generated w's from the generator Returns w's from the buffer.
stylegan_human/pti/pti_models/e4e/latent_codes_pool.py:21
Functionread_pixels
(width, height, *, pos=0, dtype='uint8', channels=3)
gui_utils/gl_utils.py:115
Methodrecurse
(scope, parent_ops, parent_vars, level)
stylegan_human/dnnlib/tflib/network.py:470
Methodrecurse
(parents)
viz/pickle_widget.py:106
Methodregister_gradients
Register the gradients of the given loss function with respect to the given variables. Intended to be called once per GPU.
stylegan_human/dnnlib/tflib/optimizer.py:116
Functionreport0
r"""Broadcasts the given set of scalars by the first process (`rank = 0`), but ignores any scalars provided by the other processes. See `repor
torch_utils/training_stats.py:103
Functionreport0
r"""Broadcasts the given set of scalars by the first process (`rank = 0`), but ignores any scalars provided by the other processes. See `repor
stylegan_human/torch_utils/training_stats.py:105
Methodreset_trainables
Re-initialize all trainable variables of this network, including sub-networks.
stylegan_human/dnnlib/tflib/network.py:197
Methodreset_vars
Re-initialize all variables of this network, including sub-networks.
stylegan_human/dnnlib/tflib/network.py:193
Methodresolution
(self)
stylegan_human/training/dataset.py:126
Methodresolution
(self)
stylegan_human/training_scripts/sg2/training/dataset.py:132
Methodresolution
(self)
stylegan_human/training_scripts/sg3/training/dataset.py:135
Methodresolution
(self)
training/dataset.py:126
Functionreverse_quad_transform
(image, quad_to_map_to, alpha)
stylegan_human/utils/face_alignment.py:227
Methodrun
(self, img, bg)
stylegan_human/PP_HumanSeg/deploy/infer.py:97
Functionsave_concat_image
(base_dir, image_latents, new_inv_image_latent, new_G, old_G, file
stylegan_human/utils/log_utils.py:51
Functionsave_obj
(obj, path)
stylegan_human/legacy.py:120
Functionsave_single_image
(base_dir, image_latent, G, file_name)
stylegan_human/utils/log_utils.py:65
Functionsave_summaries
Call FileWriter.add_summary() with all summaries in the default graph, automatically finalizing and merging them on the first call.
stylegan_human/dnnlib/tflib/autosummary.py:179
Functionsave_w
(w, G, name, method_type, results_dir)
stylegan_human/utils/log_utils.py:45
Functionscoped_by_object_id
(method)
gui_utils/imgui_utils.py:80
Methodscroll_callback
(self, window, x_offset, y_offset)
gui_utils/imgui_window.py:100
Methodset_async
(self, is_async)
visualizer_drag.py:90
Methodset_async
(self, is_async)
visualizer_drag.py:278
Functionset_cache_dir
(path: str)
stylegan_human/dnnlib/util.py:121
Functionset_cache_dir
(path: str)
dnnlib/util.py:120
Methodset_content_size
(self, width, height)
gui_utils/glfw_window.py:106
Functionset_default_style
(color_scheme='dark', spacing=9, indent=23, scrollbar=27)
gui_utils/imgui_utils.py:14
Methodset_fps_limit
(self, fps_limit)
gui_utils/glfw_window.py:124
Methodset_progressive_stage
(self, new_stage: ProgressiveStage)
stylegan_human/pti/pti_models/e4e/encoders/psp_encoders.py:169
Methodset_title
(self, title)
gui_utils/glfw_window.py:96
Methodset_var
Set the value of a given variable based on the given NumPy array. Note: This method is very inefficient -- prefer to use tflib.set_vars() when
stylegan_human/dnnlib/tflib/network.py:252
Methodsetup_as_moving_average_of
Construct a TensorFlow op that updates the variables of this network to be slightly closer to those of the given network.
stylegan_human/dnnlib/tflib/network.py:343
Functionsetup_filter
r"""Convenience function to setup 2D FIR filter for `upfirdn2d()`. Args: f: Torch tensor, numpy array, or python list of the sh
torch_utils/ops/upfirdn2d.py:70
Functionsetup_filter
r"""Convenience function to setup 2D FIR filter for `upfirdn2d()`. Args: f: Torch tensor, numpy array, or python list of the sh
stylegan_human/torch_utils/ops/upfirdn2d.py:74
Methodsetup_weight_histograms
Construct summary ops to include histograms of all trainable parameters in TensorBoard.
stylegan_human/dnnlib/tflib/network.py:537
Functionshape_to_list
Convert a Tensorflow shape to a list of ints. Retained for backwards compatibility -- use TensorShape.as_list() in new code.
stylegan_human/dnnlib/tflib/tfutil.py:41
Functionslerp
(code1, code2, alpha, DOT_THRESHOLD=0.9995)
stylegan_human/interpolation.py:27
Methodspacing
(self)
gui_utils/imgui_window.py:65
Functiontensor2im
(var)
stylegan_human/utils/data_utils.py:18
Functiontensor_to_pil
(x)
stylegan_human/utils/util.py:79
Methodtitle_bar_height
(self)
gui_utils/glfw_window.py:78
Methodtrain
(self)
stylegan_human/pti/training/coaches/multi_id_coach.py:18
Methodtrainable_gen
()
stylegan_human/training/networks_stylegan2.py:614
Methodtrainable_gen
()
stylegan_human/training_scripts/sg2/training/networks.py:588
Methodtrainable_gen
()
stylegan_human/training_scripts/sg3/training/networks_stylegan2.py:614
Methodtrainable_gen
()
training/networks_stylegan2.py:621
Functiontraining_loop
( run_dir = '.', # Output directory. training_set_kwargs = {}, # Option
stylegan_human/training/training_loop.py:90
Functiontraining_loop
( run_dir = '.', # Output directory. training_set_kwargs = {}, # Option
training/training_loop.py:90
Functiontransfer
(model, model_weights)
stylegan_human/openpose/src/util.py:35
Methodtransforms
(self)
stylegan_human/PP_HumanSeg/deploy/infer.py:46
Functiontuple_product
Calculate the product of the tuple elements.
stylegan_human/dnnlib/util.py:164
Functiontuple_product
Calculate the product of the tuple elements.
dnnlib/util.py:177
Methodunwind_key
(obj)
stylegan_human/dnnlib/tflib/network.py:392
Methodupdate_lr
(init_lr, step, num_steps, lr_rampdown_length, lr_rampup_length)
stylegan_human/insetgan.py:170
Functionupfirdn2d
(input, kernel, up=1, down=1, pad=(0, 0))
stylegan_human/torch_utils/op_edit/upfirdn2d.py:147
Functionupsample2d
r"""Upsample a batch of 2D images using the given 2D FIR filter. By default, the result is padded so that its shape is a multiple of the input.
torch_utils/ops/upfirdn2d.py:313
Functionupsample2d
r"""Upsample a batch of 2D images using the given 2D FIR filter. By default, the result is padded so that its shape is a multiple of the input.
stylegan_human/torch_utils/ops/upfirdn2d.py:310
Functionupsample_2d
r"""Upsample a batch of 2D images with the given filter. Accepts a batch of 2D images of the shape `[N, C, H, W]` or `[N, H, W, C]` and upsam
stylegan_human/dnnlib/tflib/ops/upfirdn_2d.py:171
Functionupsample_conv_2d
r"""Fused `upsample_2d()` followed by `tf.nn.conv2d()`. Padding is performed only once at the beginning, not between the operations. The fuse
stylegan_human/dnnlib/tflib/ops/upfirdn_2d.py:236
Functionvisual
(output, out_path)
stylegan_human/legacy.py:107
Methodvisual_
(path, synth_body, synth_face, body_crop, step, both=False, init_body_with_face=None)
stylegan_human/insetgan.py:131
Methodwindow_height
(self)
gui_utils/glfw_window.py:64
Methodwindow_width
(self)
gui_utils/glfw_window.py:60
← previous1,101–1,199 of 1,199, ranked by callers