def show_trace(res):
n = max(abs(min(res)), abs(max(res)))
f_line = np.arange(-n, n, 0.01)
d2l.set_figsize((3.5, 2.5))
d2l.plt.plot(f_line, [f(x) for x in f_line], '-')
d2l.plt.plot(res, [f(x) for x in res], '-o')
d2l.plt.xlabel('x')
d2l.plt.ylabel('f(x)')
def show_trace(res):
n = max(abs(min(res)), abs(max(res)), 10)
f_line = np.arange(-n, n, 0.1)
utils.set_figsize()
utils.plt.plot(f_line, [x * x for x in f_line])
utils.plt.plot(res, [x * x for x in res], '-o')
utils.plt.xlabel('x')
utils.plt.ylabel('f(x)')
utils.plt.show()
def semilogy(x_vals, y_vals, x_label, y_label, x2_vals = None, y2_vals = None, legend = None, figsize = (3.5, 2.5)):
utils.set_figsize(figsize)
utils.plt.xlabel(x_label)
utils.plt.ylabel(y_label)
utils.plt.semilogy(x_vals, y_vals)
if x2_vals and y2_vals:
utils.plt.semilogy(x2_vals, y2_vals, linestyle=":")
utils.plt.legend(legend)
utils.plt.show()
def semilogy(x_vals,
y_vals,
x_label,
y_label,
x2_vals=None,
y2_vals=None,
legend=None,
figsize=(3.5, 2.5)):
d2l.set_figsize(figsize)
d2l.plt.xlabel(x_label)
d2l.plt.ylabel(y_label)
d2l.plt.semilogy(x_vals, y_vals)
if x2_vals and y2_vals:
d2l.plt.semilogy(x2_vals, y2_vals, linestyle=':')
d2l.plt.legend(legend)
def train_ch7(optimizer_fn,
states,
hyperparams,
features,
labels,
batch_size=10,
num_epochs=2):
# 初始化模型
net, loss = d2l.linreg, d2l.squared_loss
w = torch.nn.Parameter(torch.tensor(np.random.normal(
0, 0.01, size=(features.shape[1], 1)),
dtype=torch.float32),
requires_grad=True) # [5, 1]
b = torch.nn.Parameter(torch.zeros(1, dtype=torch.float32),
requires_grad=True) # [1,]
def eval_loss():
return loss(net(features, w, b), labels).mean().item()
ls = [eval_loss()]
data_iter = torch.utils.data.DataLoader(torch.utils.data.TensorDataset(
features, labels),
batch_size,
shuffle=True)
for _ in range(num_epochs):
start = time.time()
for batch_i, (X, y) in enumerate(data_iter): # [1500, 5], [1500,]
l = loss(net(X, w, b), y).mean() # 使用平均损失
# 梯度清零
if w.grad is not None:
w.grad.data.zero_()
b.grad.data.zero_()
l.backward()
optimizer_fn([w, b], states, hyperparams) # 迭代模型参数
if (batch_i + 1) * batch_size % 100 == 0:
ls.append(eval_loss()) # 每100个样本记录下当前训练误差
# 打印结果和作图
print('loss: %f, %f sec per epoch' % (ls[-1], time.time() - start))
d2l.set_figsize()
d2l.plt.plot(np.linspace(0, num_epochs, len(ls)), ls)
d2l.plt.xlabel('epoch')
d2l.plt.ylabel('loss')
"""
图像增广
"""
import time
import torch
from torch import nn, optim
from torch.utils.data import Dataset, DataLoader
import torchvision
from PIL import Image
import sys
sys.path.append("..")
import utils
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
utils.set_figsize()
img = Image.open('C:/Users/yuange/Pictures/duck.jpg')
utils.plt.imshow(img)
def apply(img, aug, num_rows=2, num_cols=4, scale=1.5):
Y = [aug(img) for _ in range(num_rows * num_cols)]
utils.show_images(Y, num_rows, num_cols, scale)
# 翻转和剪裁
apply(img, torchvision.transforms.RandomHorizontalFlip())
apply(img, torchvision.transforms.RandomVerticalFlip())
shape_aug = torchvision.transforms.RandomResizedCrop(200, scale=(0.1, 1), ratio=(0.5, 2))
apply(img, shape_aug)
# 变化颜色
apply(img, torchvision.transforms.ColorJitter(brightness=0.5))
import numpy as np
import math
import torch
import os
from PIL import Image
import utils as d2l
d2l.set_figsize()
img = Image.open('input/img2083/img/catdog.jpg')
# d2l.plt.imshow(img) # 加分号只显示图
w, h = img.size
print("w = %d, h = %d" % (w, h))
# bbox是bounding box的缩写 561*728
dog_bbox, cat_bbox = [60, 45, 378, 516], [400, 112, 655, 493]
def bbox_to_rect(bbox, color): # 本函数已保存在d2lzh_pytorch中方便以后使用
# 将边界框(左上x, 左上y, 右下x, 右下y)格式转换成matplotlib格式：
# ((左上x, 左上y), 宽, 高)
return d2l.plt.Rectangle(xy=(bbox[0], bbox[1]),
width=bbox[2] - bbox[0],
height=bbox[3] - bbox[1],
fill=False,
edgecolor=color,
linewidth=2)
# fig = d2l.plt.imshow(img)
# fig.axes.add_patch(bbox_to_rect(dog_bbox, 'blue'))
# fig.axes.add_patch(bbox_to_rect(cat_bbox, 'red'))