medusa.recon.flame.decoders

Decoder-modules for FLAME-based reconstruction models.

See ./deca/license.md for conditions for use.

Module Contents

class medusa.recon.flame.decoders.FlameShape(n_shape=300, n_expr=100, parameters=None, device=DEVICE, **init_parameters)

Generates a FLAME-based mesh (shape only) from 3DMM parameters.

get_full_pose()

Returns the full pose vector.

forward(batch_size=None, **inputs)

Input:

shape_params: N X number of shape parameters expression_params: N X number of expression parameters pose_params: N X number of pose parameters (6)

return:d

vertices: N X V X 3 landmarks: N X number of landmarks X 3

class medusa.recon.flame.decoders.FlameLandmark(lm_type='68', lm_dim='2d', device=DEVICE)

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes:

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call to(), etc.

Note

As per the example above, an __init__() call to the parent class must be made before assignment on the child.

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

forward(v, poses)

class medusa.recon.flame.decoders.FlameTex(model_path=None, n_tex=50)

FLAME texture:

TimoBolkart/TF_FLAME FLAME texture converted from BFM: TimoBolkart/BFM_to_FLAME

forward(texcode)

texcode: [batchsize, n_tex] texture: [bz, 3, 256, 256], range: 0-1