def train_gluon_ch7(trainer_name, trainer_hyperparams, features, labels, batch_size=10, num_epochs=2):
#初始化模型
net = nn.Sequential()
net.add(nn.Dense(1))
net.initialize(init.Normal(sigma=0.01))
loss = gloss.L2Loss()
def eval_loss():
return loss(net(features), labels).mean().asscalar()
ls = [eval_loss()]
data_iter = gdata.DataLoader(gdata.ArrayDataset(features, labels), batch_size, shuffle=True)
#创建Trainer实例来迭代模型参数
trainer = gluon.Trainer(net.collect_params(), trainer_name, trainer_hyperparams)
for _ in range(num_epochs):
start = time.time()
for batch_i, (X, y) in enumerate(data_iter):
with autograd.record():
l = loss(net(X), y)
l.backward()
trainer.step(batch_size)#在Trainer实例里做梯度平均
if (batch_i+1) * batch_size % 100 == 0:
ls.append(eval_loss())
#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')
def semilogy(x_vals,
y_vals,
x_label,
y_label,
x2_vals=None,
y2_vals=None,
legend=None,
figsize=(3.5, 2.5)):
"""
作图函数
:param x_vals:
:param y_vals:
:param x_label:
:param y_label:
:param x2_vals:
:param y2_vals:
:param legend:
:param figsize:
:return:
"""
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)
d2l.plt.show()
def train_gluon_ch7(trainer_name, hyperparams, features, labels, num_epochs=2, batch_size=10):
# 初始化模型
# TODO y = XW + b
net, loss = nn.Sequential(), gloss.L2Loss()
net.add(nn.Dense(1))
net.initialize(init.Normal(sigma=0.01))
# 损失函数，用features，labels学出W,b
def eval_loss():
return loss(net(features), labels).mean().asscalar()
ls = [eval_loss()] # 记录损失变化
data_iter = gdata.DataLoader(gdata.ArrayDataset(features, labels), batch_size, shuffle=True)
# 用Trainer来迭代参数
trainer = gluon.Trainer(net.collect_params(), trainer_name, hyperparams)
for _ in range(num_epochs):
start = time.time()
for batch_i, (X,y) in enumerate(data_iter):
with autograd.record():
l = loss(net(X), y)
l.backward()
trainer.step(batch_size) # 在trainer做平均
trainer.set_learning_rate(0.1)
if (batch_i+1)*batch_size % 100 == 0: # 每100次记录下
ls.append(eval_loss())
print('loss: %f, %f sec per epoch' % (ls[-1], time.time()-start))
d2l.set_figsize(figsize=(15,5))
d2l.plt.plot(np.linspace(0, num_epochs, len(ls)), ls) # loss曲线
# 坐标轴
d2l.plt.xlabel('epochs')
d2l.plt.ylabel('loss')
def train_ch7(trainer_fn, states, hyperparams, features, labels,
batch_size=10, num_epochs=2):
net, loss = d2l.linreg, d2l.squared_loss
w = nd.random.normal(scale=0.01, shape=(features.shape[1],1))
b = nd.zeros(1)
w.attach_grad()
b.attach_grad()
def eval_loss():
return loss(net(features, w, b), labels).mean().asscalar()
ls = [eval_loss()]
data_iter = gdata.DataLoader(gdata.ArrayDataset(features, labels), batch_size, shuffle=True)
for _ in range(num_epochs):
start = time.time()
for batch_i, (X, y) in enumerate(data_iter):
with autograd.record():
l = loss (net(X, w, b), y).mean()
l.backward()
trainer_fn([w, b], states, hyperparams)
if (batch_i + 1) * batch_size % 100 ==0:
ls.append(eval_loss())
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')
def xyplot(x_vals, y_vals, name):
d2l.set_figsize(figsize=(5, 2.5))
d2l.plt.plot(x_vals.detach().numpy(), y_vals.detach().numpy())
d2l.plt.xlabel('x')
d2l.plt.ylabel(name + '(x)')
plt.show()
plt.close()
def show_trace(res):
n = max(abs(min(res)), abs(max(res)), 10)
f_line = np.arange(-n, n, 0.1)
d2l.set_figsize()
d2l.plt.plot(f_line, [x * x for x in f_line])
d2l.plt.plot(res, [x * x for x in res], '-o')
d2l.plt.xlabel('x')
d2l.plt.ylabel('f(x)')
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 y_vals:
d2l.plt.semilogy(x2_vals, y2_vals, linestyle=':')
d2l.plt.legend(legend)
d2l.plt.show()
def semilogy(x_vals, y_vals, x_label, y_label, title, x2_vals=None, y2_vals=None, legend=None, figsize=(15,5)):
d2l.set_figsize(figsize) # 显示大小
d2l.plt.figure() # 开一个空图片
d2l.plt.title(title) # 加上标题
d2l.plt.xlabel(x_label)
d2l.plt.ylabel(y_label)
d2l.plt.semilogy(x_vals, y_vals) # 曲线1
if x2_vals and y2_vals:
d2l.plt.semilogy(x2_vals, y2_vals, linestyle=':') # 曲线2
d2l.plt.legend(legend) # 曲线标注
def show_trace(res):
n = max(abs(min(res)), abs(max(res)), 10)
f_line = np.arange(-n, n, 0.1) # [-10,20]
d2l.set_figsize(figsize=(15, 5))
d2l.plt.plot(f_line, [x**2 for x in f_line]) # y=x^2
d2l.plt.plot(res, [x**2 for x in res], '-o') # x的轨迹
# 坐标轴
d2l.plt.xlabel('x')
d2l.plt.ylabel('f(x)')
color = colors[i % len(colors)]
rect = d2l.bbox_to_rect(bbox.asnumpy(), color)
axes.add_patch(rect)
if labels and len(labels) > i:
text_color = 'k' if color == 'w' else 'w'
axes.text(rect.xy[0],
rect.xy[1],
labels[i],
va='center',
ha='center',
fontsize=9,
color=text_color,
bbox=dict(facecolor=color, lw=0))
d2l.set_figsize()
bbox_scale = nd.array((w, h, w, h))
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale, [
's=0.75, r=1', 's=0.5, r=1', 's=0.25, r=1', 's=0.75, r=2', 's=0.75, r=0.5'
])
#9.4.2-交并比
#9.4.3-标注训练集的锚框
ground_truth = nd.array([[0, 0.1, 0.08, 0.52, 0.92], [1, 0.55, 0.2, 0.9,
0.88]])
anchors = nd.array([[0, 0.1, 0.2, 0.3], [0.15, 0.2, 0.4, 0.4],
[0.63, 0.05, 0.88, 0.98], [0.66, 0.45, 0.8, 0.8],
[0.57, 0.3, 0.92, 0.9]])
fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, ground_truth[:, 1:] * bbox_scale, ['dog', 'cat'], 'k')
show_bboxes(fig.axes, anchors * bbox_scale, ['0', '1', '2', '3', '4'])
def xyplot(x_vals, y_vals, name):
d2l.set_figsize(figsize=(5, 2.5))
d2l.plt.plot(x_vals.asnumpy(), y_vals.asnumpy())
d2l.plt.xlabel('x')
d2l.plt.ylabel(name + '(x)')
d2l.plt.show()
img = image.imread('../img/pikachu.jpg')
feature = image.imresize(img, 256, 256).astype('float32')
X = feature.transpose((2, 0, 1)).expand_dims(axis=0)
def predict(X):
anchor, cls_preds, bbox_preds = net(X.as_in_context(ctx))
cls_probs = cls_preds.softmax().transpose((0, 2, 1))
output = contrib.nd.MultiBoxDetection(cls_probs, bbox_preds, anchors)
idx = [i for i, row in enumerate(output[0]) if row[0].asscalar() != -1]
return output[0, idx]
output = predict(X)
d2l.set_figsize((5, 5))
def display(img, output, threshold):
fig = d2l.plt.imshow(img.asnumpy())
for row in output:
score = row[1].asscalar()
if score < threshold:
continue
h, w = img.shape[0:2]
bbox = [row[2:6] * nd.array((w, h, w, h), ctx=row.context)]
d2l.show_bboxes(fig.axes, bbox, '%.2f' % score, 'w')
display(img, output, threshold=0.3)
def xyplot(x_vals, y_vals, name):
d2l.set_figsize(figsize=(5, 2.5))
d2l.plt.plot(x_vals.asnumpy(), y_vals.asnumpy())
d2l.plt.xlabel("x")
d2l.plt.ylabel(name + "(x)")
def xypolt(x, y, name):
d2l.set_figsize(figsize=(15, 5))
d2l.plt.figure()
d2l.plt.plot(x.asnumpy(), y.asnumpy())
d2l.plt.xlabel('x')
d2l.plt.ylabel(name + '(x)')
""" @Author: [email protected] @Date: 2020-06-08 18:05:53 @LastEditors: [email protected] @LastEditTime: 2020-06-10 14:20:52 @FilePath: /d2l-zh/optimization-algorithm/optimization-and-deepling-learning.py """ import d2lzh as d2l from mpl_toolkits import mplot3d import numpy as np def f(x): return x * np.cos(np.pi * x) if __name__ == "__main__": d2l.set_figsize((4.5, 2.5)) x = np.arange(-1.0, 2.0, 0.1) fig, = d2l.plt.plot(x, f(x)) fig.axes.annotate('local minimum', xy=(-0.3, -0.25), xytext=(-0.77, -1.0), arrowprops=dict(arrowstyle='->')) fig.axes.annotate('global minimum', xy=(1.1, -0.95), xytext=(0.6, 0.8), arrowprops=dict(arrowstyle='->')) d2l.plt.xlabel('x') d2l.plt.ylabel('f(x)') d2l.plt.show()
import d2lzh as d2l
from mpl_toolkits import mplot3d
import numpy as np
# TODO f(x)=xcos(pi*x) [-1.0, 2.0]
def f(x):
return x * np.cos(np.pi * x)
d2l.set_figsize(figsize=(15, 5))
x = np.arange(-1.0, 2.0, 0.1)
fig, = d2l.plt.plot(x, f(x))
fig.axes.annotate('local minimum',
xy=(-0.3, -0.25),
xytext=(-0.77, -1.0),
arrowprops=dict(arrowstyle='->'))
fig.axes.annotate('global minimum',
xy=(1.1, -0.95),
xytext=(0.6, 0.8),
arrowprops=dict(arrowstyle='->'))
d2l.plt.xlabel('x')
d2l.plt.ylabel('f(x)')
# TODO f(x)=x^3 [-2, 2.0]
x = np.arange(-2.0, 2.0, 0.1)
fig, = d2l.plt.plot(x, x**3)
# 给曲线添加一些注释,xy是标记点,xytext是文字的位置
fig.axes.annotate('saddle point',
xy=(0, 0),
xytext=(-0.52, -5.0),