Acceleration

Module containing helper functions and classes around acceleration

---

source

SGD

 SGD (params, lr, wd=0.0)

Initialize self. See help(type(self)) for accurate signature.

---

source

Momentum

 Momentum (params, lr, wd=0.0, mom=0.9)

Initialize self. See help(type(self)) for accurate signature.

---

source

RMSProp

 RMSProp (params, lr, wd=0.0, sqr_mom=0.99, eps=1e-05)

Initialize self. See help(type(self)) for accurate signature.

---

source

Adam

 Adam (params, lr, wd=0.0, beta1=0.9, beta2=0.99, eps=1e-05)

Initialize self. See help(type(self)) for accurate signature.

---

source

SchedulerS

 SchedulerS (scheduler_class)

Initialize self. See help(type(self)) for accurate signature.

---

source

conv_conn

 conv_conn (in_c, out_c, kernel_size=3, stride=2)

---

source

ResBlock

 ResBlock (in_c, out_c, stride=2)

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 :meth:to, etc.

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

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

---

source

resnet

 resnet ()

---

source

ModelMonitorS

 ModelMonitorS (modules)

Initialize self. See help(type(self)) for accurate signature.

---

source

AugmentS

 AugmentS (transform)

Initialize self. See help(type(self)) for accurate signature.