TensorBoard:TensorFlow中强大的可视化工具
将python程序中需要记录的可视化数据,保存成硬盘上可以展示的文件(event file),再通过TensorBoard进行可视化的展示,就可以通过web端查看。
tensorboard --logdir=yourpath
--port=端口
--bind_all
最后一个参数代表运行绑定端口,让其他ip的地址通过端口也能访问,并不只让127.0.0.1访问
import numpy as np
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter(comment='test_tensorboard')
for x in range(100):
writer.add_scalar('y=2x', x * 2, x)
writer.add_scalar('y=pow(2, x)', 2 ** x, x)
writer.add_scalars('data/scalar_group', {"xsinx": x * np.sin(x),
"xcosx": x * np.cos(x),
"arctanx": np.arctan(x)}, x)
writer.close()
上诉代码执行完毕生成,文件(runs)–(Aug22_07-18-03_db50a46be61atest_tensorboard)–下面是几个标量的文件夹和event file
writer = SummaryWriter(comment='test_comment', filename_suffix="test_suffix")
for x in range(2):
np.random.seed(x)
data_union = np.arange(100)
data_normal = np.random.normal(size=1000)
writer.add_histogram('distribution union', data_union, x)
writer.add_histogram('distribution normal', data_normal, x)
plt.subplot(121).hist(data_union, label="union")
plt.subplot(122).hist(data_normal, label="normal")
plt.legend()
plt.show()
writer.close()
接口中的参数:global_step,主要体现一个tag中有几幅图,并且在y轴上体现出来,如上图。
train_curve = list()
valid_curve = list()
iter_count = 0
# 构建 SummaryWriter
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
for epoch in range(MAX_EPOCH):
loss_mean = 0.
correct = 0.
total = 0.
net.train()
for i, data in enumerate(train_loader):
iter_count += 1
# forward
inputs, labels = data
outputs = net(inputs)
# backward
optimizer.zero_grad()
loss = criterion(outputs, labels)
loss.backward()
# update weights
optimizer.step()
# 统计分类情况
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).squeeze().sum().numpy()
# 打印训练信息
loss_mean += loss.item()
train_curve.append(loss.item())
if (i+1) % log_interval == 0:
loss_mean = loss_mean / log_interval
print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
epoch, MAX_EPOCH, i+1, len(train_loader), loss_mean, correct / total))
loss_mean = 0.
# 记录数据,保存于event file
writer.add_scalars("Loss", {"Train": loss.item()}, iter_count)
writer.add_scalars("Accuracy", {"Train": correct / total}, iter_count)
# 每个epoch,记录梯度,权值
for name, param in net.named_parameters():
writer.add_histogram(name + '_grad', param.grad, epoch)
writer.add_histogram(name + '_data', param, epoch)
scheduler.step() # 更新学习率
# validate the model
if (epoch+1) % val_interval == 0:
correct_val = 0.
total_val = 0.
loss_val = 0.
net.eval()
with torch.no_grad():
for j, data in enumerate(valid_loader):
inputs, labels = data
outputs = net(inputs)
loss = criterion(outputs, labels)
_, predicted = torch.max(outputs.data, 1)
total_val += labels.size(0)
correct_val += (predicted == labels).squeeze().sum().numpy()
loss_val += loss.item()
loss_mean_epoch = loss_val / len(valid_loader) # 计算一个epoch的loss均值
valid_curve.append(loss_mean_epoch) # 记录每个epoch的loss
print("Valid:\t Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
epoch, MAX_EPOCH, j+1, len(valid_loader), loss_mean_epoch, correct_val / total_val))
# 记录数据,保存于event file
writer.add_scalars("Loss", {"Valid": loss_mean_epoch}, iter_count)
writer.add_scalars("Accuracy", {"Valid": correct_val / total_val}, iter_count)
最后一个参数,主要是有的图像的通道数在维度上不一样。有的是灰度图(通道数为1)
第二个参数,对于图像上数据,如果有的图像经过了模型归一化,其中的数据已经不是0-255,而是0-1的浮点数,这时候,如果发现数据都在0-1,会对其乘以255来可视化。
此方法,会在一个窗口上通过进度条的形式,拉动x轴,分别展示多个图像,如图:
不是tensorboard的SummaryWriter对象中的方法,而是来自torchversion.utils中的方法。
一般是用这个方法绘制一个网格图像,然后用SummaryWriter的add_image去添加一个图像。
功能:制作网格图像
• tensor:图像数据, BCH*W形式
• nrow:行数(列数自动计算)
• padding:图像间距(像素单位)
• normalize:是否将像素值标准化
• range:标准化范围
• scale_each:是否单张图维度标准化
• pad_value:padding的像素值
结果如下图:
import torch.nn as nn
from PIL import Image
import torchvision.transforms as transforms
from torch.utils.tensorboard import SummaryWriter
import torchvision.utils as vutils
import os
import torch
import sys
hello_pytorch_DIR = os.path.abspath(os.path.dirname(__file__)+os.path.sep+".."+os.path.sep+"..")
sys.path.append(hello_pytorch_DIR)
from tools.common_tools import set_seed
import torchvision.models as models
set_seed(1) # 设置随机种子
# ----------------------------------- kernel visualization -----------------------------------
# flag = 0
flag = 1
if flag:
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
alexnet = models.alexnet(pretrained=True)
kernel_num = -1
vis_max = 1
# 避免pytorch1.7下的一个小bug,增加 torch.no_grad
with torch.no_grad():
for sub_module in alexnet.modules():
if isinstance(sub_module, nn.Conv2d):
kernel_num += 1
if kernel_num > vis_max:
break
kernels = sub_module.weight
c_out, c_int, k_w, k_h = tuple(kernels.shape)
for o_idx in range(c_out):
kernel_idx = kernels[o_idx, :, :, :].unsqueeze(1) # make_grid需要 BCHW,这里拓展C维度。其实拿出来的是原卷积核的 CHW,只不过在把原C当作B,然后扩展一个C
kernel_grid = vutils.make_grid(kernel_idx, normalize=True, scale_each=True, nrow=c_int)
writer.add_image('{}_Convlayer_split_in_channel'.format(kernel_num), kernel_grid, global_step=o_idx)
kernel_all = kernels.view(-1, 3, k_h, k_w) # 3, h, w
kernel_grid = vutils.make_grid(kernel_all, normalize=True, scale_each=True, nrow=8) # c, h, w
writer.add_image('{}_all'.format(kernel_num), kernel_grid, global_step=322)
print("{}_convlayer shape:{}".format(kernel_num, tuple(kernels.shape)))
writer.close()
# ----------------------------------- feature map visualization -----------------------------------
# flag = 0
flag = 1
if flag:
with torch.no_grad():
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
# 数据
path_img = "./lena.png" # your path to image
normMean = [0.49139968, 0.48215827, 0.44653124]
normStd = [0.24703233, 0.24348505, 0.26158768]
norm_transform = transforms.Normalize(normMean, normStd)
img_transforms = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
norm_transform
])
img_pil = Image.open(path_img).convert('RGB')
if img_transforms is not None:
img_tensor = img_transforms(img_pil)
img_tensor.unsqueeze_(0) # chw --> bchw
# 模型
alexnet = models.alexnet(pretrained=True)
# forward
convlayer1 = alexnet.features[0]
fmap_1 = convlayer1(img_tensor)
# 预处理
fmap_1.transpose_(0, 1) # bchw=(1, 64, 55, 55) --> (64, 1, 55, 55) 为了展示,把64的c换成b
fmap_1_grid = vutils.make_grid(fmap_1, normalize=True, scale_each=True, nrow=8)
writer.add_image('feature map in conv1', fmap_1_grid, global_step=322)
writer.close()
功能:可视化模型计算图
• model:模型,必须是 nn.Module
• input_to_model:输出给模型的数据
• verbose:是否打印计算图结构信息
writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")
# 模型
fake_img = torch.randn(1, 3, 32, 32)
lenet = LeNet(classes=2)
writer.add_graph(lenet, fake_img)
writer.close()