# nn
------------------------------------------------------------------------
source
### make_property_predictor
``` python
def make_property_predictor(
key, d:int=512, ldmin:float=0.0031622776601683794, ldmax:float=1995.2623149688789, hidden_layer:int=512,
ffdim:int=512, nhead:int=32, nlayers:int=6, dout:int=10, act_fn:jax._src.custom_derivatives.custom_jvp=relu,
initializer:function=he_normal, attention_backend:NoneType=None, block_size:int=128, bias:bool=True,
mask_fn:function=mask_fn
):
```
------------------------------------------------------------------------
source
### make_spectrum_encoder
``` python
def make_spectrum_encoder(
key, d:int=512, ldmin:float=0.0031622776601683794, ldmax:float=1995.2623149688789, hidden_layer:int=512,
ffdim:int=512, nhead:int=32, nlayers:int=6, act_fn:jax._src.custom_derivatives.custom_jvp=relu,
initializer:function=he_normal, attention_backend:NoneType=None, block_size:int=128, mask_fn:function=mask_fn
):
```
------------------------------------------------------------------------
source
### make_transformer_block
``` python
def make_transformer_block(
key, nembd, nhead, ffdim:NoneType=None, attention_backend:NoneType=None, block_size:int=128,
act_fn:jax._src.custom_derivatives.custom_jvp=relu, initializer:function=he_normal, bias:bool=True
):
```
------------------------------------------------------------------------
source
### make_multi_head_attention
``` python
def make_multi_head_attention(
key, nembd, nhead, attention_backend:NoneType=None, block_size:int=128, initializer:function=he_normal
):
```
------------------------------------------------------------------------
source
### blockwise_attention
``` python
def blockwise_attention(
q, k, v, mask:NoneType=None, block_size:int=128
):
```
*q: (B, N, T, H), k: (B, N, T, H), v: (B, N, T, H)*
------------------------------------------------------------------------
source
### mask_fn
``` python
def mask_fn(
x
):
```
------------------------------------------------------------------------
source
### make_peak_embedding
``` python
def make_peak_embedding(
key, d:int=512, hidden_layer:int=512, ldmin:float=0.0031622776601683794, ldmax:float=1995.2623149688789,
act_fn:jax._src.custom_derivatives.custom_jvp=relu, initializer:function=he_normal, bias:bool=True
):
```
------------------------------------------------------------------------
source
### make_sinusoidal_embedding
``` python
def make_sinusoidal_embedding(
d:int=512, ldmin:float=0.0031622776601683794, ldmax:float=1995.2623149688789
):
```
------------------------------------------------------------------------
source
### make_layernorm2d
``` python
def make_layernorm2d(
key, num_features, eps:float=1e-05, offset:bool=True, ndims:int=4
):
```
------------------------------------------------------------------------
source
### make_layernorm1d
``` python
def make_layernorm1d(
key, num_features, eps:float=1e-05, offset:bool=True
):
```
------------------------------------------------------------------------
source
### make_squeeze
``` python
def make_squeeze(
key, dims:NoneType=None
):
```
------------------------------------------------------------------------
source
### make_conv2d
``` python
def make_conv2d(
key, cho, chi, ks:tuple=(3, 3), padding:str='SAME', strides:tuple=(1, 1),
act_fn:jax._src.custom_derivatives.custom_jvp=relu, initializer:function=he_normal, bias:bool=True,
act:bool=True
):
```
------------------------------------------------------------------------
source
### make_ffn
``` python
def make_ffn(
key, din, dout, hidden_layer:int=512, act_fn:jax._src.custom_derivatives.custom_jvp=relu,
initializer:function=he_normal, bias:bool=True
):
```
------------------------------------------------------------------------
source
### make_linear
``` python
def make_linear(
key, fan_in, fan_out, act_fn:jax._src.custom_derivatives.custom_jvp=relu, initializer:function=he_normal,
bias:bool=True, act:bool=True
):
```