代码拉取完成,页面将自动刷新
WithLossCell
is essentially a Cell
that contains the loss function. To build WithLossCell
, you need to define the network and loss function in advance.
The following uses an example to describe how to use this function. First, you need to build a network. The content is as follows:
import numpy as np
import mindspore.context as context
import mindspore.nn as nn
from mindspore import Tensor
from mindspore.nn import TrainOneStepCell, WithLossCell
from mindspore.nn.optim import Momentum
import mindspore.ops as ops
context.set_context(mode=context.GRAPH_MODE, device_target="GPU")
class LeNet5(nn.Cell):
"""
Lenet network
Args:
num_class (int): Number of classes. Default: 10.
num_channel (int): Number of channels. Default: 1.
Returns:
Tensor, output tensor
Examples:
>>> LeNet(num_class=10)
"""
def __init__(self, num_class=10, num_channel=1, include_top=True):
super(LeNet5, self).__init__()
self.conv1 = nn.Conv2d(num_channel, 6, 5, pad_mode='valid')
self.conv2 = nn.Conv2d(6, 16, 5, pad_mode='valid')
self.relu = nn.ReLU()
self.max_pool2d = nn.MaxPool2d(kernel_size=2, stride=2)
self.include_top = include_top
if self.include_top:
self.flatten = nn.Flatten()
self.fc1 = nn.Dense(16 * 5 * 5, 120, weight_init=Normal(0.02))
self.fc2 = nn.Dense(120, 84, weight_init=Normal(0.02))
self.fc3 = nn.Dense(84, num_class, weight_init=Normal(0.02))
def construct(self, x):
x = self.conv1(x)
x = self.relu(x)
x = self.max_pool2d(x)
x = self.conv2(x)
x = self.relu(x)
x = self.max_pool2d(x)
if not self.include_top:
return x
x = self.flatten(x)
x = self.relu(self.fc1(x))
x = self.relu(self.fc2(x))
x = self.fc3(x)
return x
The following is an example of using WithLossCell
. Define the network and loss functions, create a WithLossCell
, and input the input data and label data. WithLossCell
returns the calculation result based on the network and loss functions.
data = Tensor(np.ones([32, 1, 32, 32]).astype(np.float32) * 0.01)
label = Tensor(np.ones([32]).astype(np.int32))
net = LeNet5()
criterion = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
net_with_criterion = WithLossCell(net, criterion)
loss = net_with_criterion(data, label)
print("+++++++++Loss+++++++++++++")
print(loss)
The following information is displayed:
+++++++++Loss+++++++++++++
2.302585
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。