search

neeek2303 / EMOPortraits

Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars
311 stars 17 forks source link

typo? #25

Open johndpope opened 2 weeks ago

johndpope commented 2 weeks ago

https://github.com/neeek2303/EMOPortraits/blob/main/networks/volumetric_avatar/local_encoder_back.py#L36

class Config:
    gen_upsampling_type: str
    gen_downsampling_type: str
    gen_num_channels: int
    enc_channel_mult: int
    norm_layer_type: str
    num_gpus: int
    gen_input_image_size: int
    gen_latent_texture_size: int
    gen_max_channels: int
    enc_block_type: int
    gen_activation_type: str
    seg_out_channels: int
 **in_channels= int**
    in_channels: int

File "/media/oem/12TB/EMOPortraits/models/stage_1/volumetric_avatar/va_arguments.py", line 696, in local_encoder_back_cfg return volumetric_avatar.LocalEncoderBack.Config( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: LocalEncoderBack.Config.init() got an unexpected keyword argument 'in_channels'