guanjihuan/py.guanjihuan.com
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

0.1.99

Browse Source
This commit is contained in:
guanjihuan 2024-05-10 06:00:12 +08:00
parent 831af1a157
commit e4b96d78dd
3 changed files with 26 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
PyPI/setup.cfg
View File

@ -1,7 +1,7 @@
[metadata] [metadata]
# replace with your username: # replace with your username:
name = guan name = guan
version = 0.1.98 version = 0.1.99
author = guanjihuan author = guanjihuan
author_email = guanjihuan@163.com author_email = guanjihuan@163.com
description = An open source python package description = An open source python package

2
PyPI/src/guan.egg-info/PKG-INFO
View File

@ -1,6 +1,6 @@
Metadata-Version: 2.1 Metadata-Version: 2.1
Name: guan Name: guan
Version: 0.1.98 Version: 0.1.99
Summary: An open source python package Summary: An open source python package
Home-page: https://py.guanjihuan.com Home-page: https://py.guanjihuan.com
Author: guanjihuan Author: guanjihuan

24
PyPI/src/guan/machine_learning.py
View File

@ -18,6 +18,10 @@ def fully_connected_neural_network_with_one_hidden_layer(input_size=1, hidden_si
hidden_output = torch.nn.functional.sigmoid(self.hidden_layer(x)) hidden_output = torch.nn.functional.sigmoid(self.hidden_layer(x))
elif activation == 'tanh': elif activation == 'tanh':
hidden_output = torch.nn.functional.tanh(self.hidden_layer(x)) hidden_output = torch.nn.functional.tanh(self.hidden_layer(x))
elif activation == 'gelu':
hidden_output = torch.nn.functional.gelu(self.hidden_layer(x))
elif activation == 'silu':
hidden_output = torch.nn.functional.silu(self.hidden_layer(x))
else: else:
hidden_output = self.hidden_layer(x) hidden_output = self.hidden_layer(x)
output = self.output_layer(hidden_output) output = self.output_layer(hidden_output)
@ -44,6 +48,10 @@ def fully_connected_neural_network_with_two_hidden_layers(input_size=1, hidden_s
hidden_output_1 = torch.nn.functional.sigmoid(self.hidden_layer_1(x)) hidden_output_1 = torch.nn.functional.sigmoid(self.hidden_layer_1(x))
elif activation_1 == 'tanh': elif activation_1 == 'tanh':
hidden_output_1 = torch.nn.functional.tanh(self.hidden_layer_1(x)) hidden_output_1 = torch.nn.functional.tanh(self.hidden_layer_1(x))
elif activation_1 == 'gelu':
hidden_output_1 = torch.nn.functional.gelu(self.hidden_layer_1(x))
elif activation_1 == 'silu':
hidden_output_1 = torch.nn.functional.silu(self.hidden_layer_1(x))
else: else:
hidden_output_1 = self.hidden_layer_1(x) hidden_output_1 = self.hidden_layer_1(x)
@ -55,6 +63,10 @@ def fully_connected_neural_network_with_two_hidden_layers(input_size=1, hidden_s
hidden_output_2 = torch.nn.functional.sigmoid(self.hidden_layer_2(hidden_output_1)) hidden_output_2 = torch.nn.functional.sigmoid(self.hidden_layer_2(hidden_output_1))
elif activation_2 == 'tanh': elif activation_2 == 'tanh':
hidden_output_2 = torch.nn.functional.tanh(self.hidden_layer_2(hidden_output_1)) hidden_output_2 = torch.nn.functional.tanh(self.hidden_layer_2(hidden_output_1))
elif activation_2 == 'gelu':
hidden_output_2 = torch.nn.functional.gelu(self.hidden_layer_2(hidden_output_1))
elif activation_2 == 'silu':
hidden_output_2 = torch.nn.functional.silu(self.hidden_layer_2(hidden_output_1))
else: else:
hidden_output_2 = self.hidden_layer_2(hidden_output_1) hidden_output_2 = self.hidden_layer_2(hidden_output_1)
@ -83,6 +95,10 @@ def fully_connected_neural_network_with_three_hidden_layers(input_size=1, hidden
hidden_output_1 = torch.nn.functional.sigmoid(self.hidden_layer_1(x)) hidden_output_1 = torch.nn.functional.sigmoid(self.hidden_layer_1(x))
elif activation_1 == 'tanh': elif activation_1 == 'tanh':
hidden_output_1 = torch.nn.functional.tanh(self.hidden_layer_1(x)) hidden_output_1 = torch.nn.functional.tanh(self.hidden_layer_1(x))
elif activation_1 == 'gelu':
hidden_output_1 = torch.nn.functional.gelu(self.hidden_layer_1(x))
elif activation_1 == 'silu':
hidden_output_1 = torch.nn.functional.silu(self.hidden_layer_1(x))
else: else:
hidden_output_1 = self.hidden_layer_1(x) hidden_output_1 = self.hidden_layer_1(x)
@ -94,6 +110,10 @@ def fully_connected_neural_network_with_three_hidden_layers(input_size=1, hidden
hidden_output_2 = torch.nn.functional.sigmoid(self.hidden_layer_2(hidden_output_1)) hidden_output_2 = torch.nn.functional.sigmoid(self.hidden_layer_2(hidden_output_1))
elif activation_2 == 'tanh': elif activation_2 == 'tanh':
hidden_output_2 = torch.nn.functional.tanh(self.hidden_layer_2(hidden_output_1)) hidden_output_2 = torch.nn.functional.tanh(self.hidden_layer_2(hidden_output_1))
elif activation_2 == 'gelu':
hidden_output_2 = torch.nn.functional.gelu(self.hidden_layer_2(hidden_output_1))
elif activation_2 == 'silu':
hidden_output_2 = torch.nn.functional.silu(self.hidden_layer_2(hidden_output_1))
else: else:
hidden_output_2 = self.hidden_layer_2(hidden_output_1) hidden_output_2 = self.hidden_layer_2(hidden_output_1)
@ -105,6 +125,10 @@ def fully_connected_neural_network_with_three_hidden_layers(input_size=1, hidden
hidden_output_3 = torch.nn.functional.sigmoid(self.hidden_layer_3(hidden_output_2)) hidden_output_3 = torch.nn.functional.sigmoid(self.hidden_layer_3(hidden_output_2))
elif activation_3 == 'tanh': elif activation_3 == 'tanh':
hidden_output_3 = torch.nn.functional.tanh(self.hidden_layer_3(hidden_output_2)) hidden_output_3 = torch.nn.functional.tanh(self.hidden_layer_3(hidden_output_2))
elif activation_3 == 'gelu':
hidden_output_3 = torch.nn.functional.gelu(self.hidden_layer_3(hidden_output_2))
elif activation_3 == 'silu':
hidden_output_3 = torch.nn.functional.silu(self.hidden_layer_3(hidden_output_2))
else: else:
hidden_output_3 = self.hidden_layer_3(hidden_output_2) hidden_output_3 = self.hidden_layer_3(hidden_output_2)