r"""Find edges of the input image and filters them using the Canny algorithm. .. image:: _static/img/canny.png Args: input: input imag

Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).

Create a 1D, 2D, or 3D convolution module.

Function: ---------- Convert Transform Matrix 'trans' into 'cv2_trans' which could be directly used by cv2.warpAffine():

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo

Decode landm from predictions using priors to undo the encoding we did for offset regression at train time. Args: pre (tensor): landm

DropBlock. See https://arxiv.org/pdf/1810.12890.pdf DropBlock with an experimental gaussian noise option. This layer has been tested on a few tra

DropBlock. See https://arxiv.org/pdf/1810.12890.pdf DropBlock with an experimental gaussian noise option. Simplied from above without concern for

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). From: https://github.com/huggingface/pytorch-image-models

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E

Computes efficient dot-product attention given query, transposed key, and value. This is efficient version of attention presented in https

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Takes a style and compares it to the prompt and negative prompt. If the style matches, returns True plus the prompt and negative prompt with

* This function fits the target element to the screen by calculating * the required scale and offsets. It also updates the global variables