Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/ZhengyuZhao/PerC-Adversarial
/ functions
Functions
17 in github.com/ZhengyuZhao/PerC-Adversarial
⨍
Functions
17
◇
Types & classes
2
↓ 6 callers
Function
radians
(n)
differential_color_functions.py:55
↓ 5 callers
Function
xyz_lab
(xyz_image,device)
differential_color_functions.py:16
↓ 4 callers
Function
rgb2lab_diff
Function to convert a batch of image tensors from RGB space to CIELAB space. parameters: xn, yn, zn are the CIE XYZ tristimulus values of
differential_color_functions.py:26
↓ 2 callers
Function
ciede2000_diff
CIEDE2000 metric to claculate the color distance map for a batch of image tensors defined in CIELAB space
differential_color_functions.py:90
↓ 2 callers
Function
hpf_diff
(x, y)
differential_color_functions.py:56
↓ 1 callers
Method
_arctanh
(x: torch.Tensor, eps: float = 1e-6)
perc_cw.py:68
↓ 1 callers
Method
_step
(self, model: nn.Module, optimizer: optim.Optimizer, inputs: torch.Tensor, tinputs: torch.Tensor,
perc_cw.py:72
↓ 1 callers
Function
ahpf_diff
(c1, c2, h1p, h2p)
differential_color_functions.py:76
↓ 1 callers
Function
degrees
(n)
differential_color_functions.py:54
↓ 1 callers
Function
dhpf_diff
(c1, c2, h1p, h2p)
differential_color_functions.py:66
↓ 1 callers
Function
quantization
quantize the continus image tensors into 255 levels (8 bit encoding)
perc_al.py:10
↓ 1 callers
Function
quantization
quantize the continus image tensors into 255 levels (8 bit encoding)
perc_cw.py:8
↓ 1 callers
Function
rgb2xyz
(rgb_image,device)
differential_color_functions.py:4
Method
__init__
(self, max_iterations: int = 1000, alpha_l_init: float = 1., #for relat
perc_al.py:35
Method
__init__
(self, image_constraints: Tuple[float, float] = [0,1], num_classes: int = 10
perc_cw.py:37
Method
adversary
Performs the adversary of the model given the inputs and labels. Parameters ---------- model : nn.Module
perc_al.py:49
Method
adversary
Performs the adversary of the model given the inputs and labels. Parameters ---------- model : nn.Module
perc_cw.py:100