pytorch 利用tensorboard显示loss，acc曲线等
运行环境：
python3.6.9
pytorch1.13.1
cuda10.0
cudnn7.5.1
tensorboard显示
运行PointRCNN算法进行training，得出events.out.tfevents.1592297776.hkd-Precision-7920-Tower
打开终端输入：tensorboard --logdir path/to/tensorboard_logs/
会有输出：TensorBoard 1.6.0 at http://iccd:6006 (Press CTRL+C to quit)
将上述链接复制到浏览器中打开便可以显示该训练参数（tensorboard）
tensorboard记录
from tensorboard_logger import Logger
logger = Logger(logdir="./tensorboard_logs", flush_secs=10)
...
def train(net, optimizer):
for epoch in range(epoch_nums):
net.train()
for batch_idx, (inputs, targets) in enumerate(trainloader):
inputs = Variable(inputs, requires_grad=True).cuda()
targets = targets.cuda()
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, targets)
loss.backward()
optimizer.step()
train_loss += loss.item()
...
# 记录所需的变量
logger.log_value('avg_loss', train_loss/(batch_idx+1), epoch*len(trainloader) + batch_idx)
logger.log_value('loss', loss.item(), epoch*len(trainloader) + batch_idx)
logger.log_value('acc', 100. * correct / total, epoch*len(trainloader) + batch_idx)
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请联系我们举报，一经查实，本站将立刻删除。
发布者：全栈程序员-站长，转载请注明出处：https://javaforall.net/2151.html原文链接：https://javaforall.net
![探秘X86架构CPU流水线[通俗易懂]](https://javaforall.net/wp-content/uploads/2020/11/2020110817443450-480x300.jpg)
