MCPcopy Create free account
hub / github.com/FunAudioLLM/ThinkSound / __init__

Method __init__

ThinkSound/models/diffusion.py:409–489  ·  view source on GitHub ↗
(
        self,
        io_channels = 2,
        depth=14,
        n_attn_layers = 6,
        channels = [128, 128, 256, 256] + [512] * 10,
        cond_dim = 0,
        cond_noise_aug = False,
        kernel_size = 5,
        learned_resample = False,
        strides = [2] * 13,
        conv_bias = True,
        use_snake = False
    )

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 8

FourierFeaturesClass · 0.85
SkipBlockClass · 0.85
Downsample1d_2Function · 0.85
Downsample1dClass · 0.85
SelfAttention1dClass · 0.85
Upsample1d_2Function · 0.85
Upsample1dClass · 0.85
__init__Method · 0.45

Tested by

no test coverage detected