""" This script demonstrates the use of a convolutional LSTM network.
This network is used to predict the next frame of an artificially
generated movie which contains moving squares.
"""from keras.models import Sequential
from keras.layers.convolutional import Conv3D
from keras.layers.convolutional_recurrent import ConvLSTM2D
from keras.layers.normalization import BatchNormalization
import numpy as np
import pylab as plt
# We create a layer which take as input movies of shape# (n_frames, width, height, channels) and returns a movie# of identical shape.
seq = Sequential()
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
input_shape=(None, 40, 40, 1),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
seq.add(BatchNormalization())
seq.add(Conv3D(filters=1, kernel_size=(3, 3, 3),
activation='sigmoid',
padding='same', data_format='channels_last'))
seq.compile(loss='binary_crossentropy', optimizer='adadelta')
# Artificial data generation:# Generate movies with 3 to 7 moving squares inside.# The squares are of shape 1x1 or 2x2 pixels,# which move linearly over time.# For convenience we first create movies with bigger width and height (80x80)# and at the end we select a 40x40 window.defgenerate_movies(n_samples=1200, n_frames=15):
row = 80
col = 80
noisy_movies = np.zeros((n_samples, n_frames, row, col, 1), dtype=np.float)
shifted_movies = np.zeros((n_samples, n_frames, row, col, 1),
dtype=np.float)
for i inrange(n_samples):
# Add 3 to 7 moving squares
n = np.random.randint(3, 8)
for j inrange(n):
# Initial position
xstart = np.random.randint(20, 60)
ystart = np.random.randint(20, 60)
# Direction of motion
directionx = np.random.randint(0, 3) - 1
directiony = np.random.randint(0, 3) - 1# Size of the square
w = np.random.randint(2, 4)
for t inrange(n_frames):
x_shift = xstart + directionx * t
y_shift = ystart + directiony * t
noisy_movies[i, t, x_shift - w: x_shift + w,
y_shift - w: y_shift + w, 0] += 1# Make it more robust by adding noise.# The idea is that if during inference,# the value of the pixel is not exactly one,# we need to train the network to be robust and still# consider it as a pixel belonging to a square.if np.random.randint(0, 2):
noise_f = (-1)**np.random.randint(0, 2)
noisy_movies[i, t,
x_shift - w - 1: x_shift + w + 1,
y_shift - w - 1: y_shift + w + 1,
0] += noise_f * 0.1# Shift the ground truth by 1
x_shift = xstart + directionx * (t + 1)
y_shift = ystart + directiony * (t + 1)
shifted_movies[i, t, x_shift - w: x_shift + w,
y_shift - w: y_shift + w, 0] += 1# Cut to a 40x40 window
noisy_movies = noisy_movies[::, ::, 20:60, 20:60, ::]
shifted_movies = shifted_movies[::, ::, 20:60, 20:60, ::]
noisy_movies[noisy_movies >= 1] = 1
shifted_movies[shifted_movies >= 1] = 1return noisy_movies, shifted_movies
# Train the network
noisy_movies, shifted_movies = generate_movies(n_samples=1200)
'''
seq.fit(noisy_movies[:1000], shifted_movies[:1000], batch_size=10,
epochs=300, validation_split=0.05)
# Testing the network on one movie
# feed it with the first 7 positions and then
# predict the new positions
which = 1004
track = noisy_movies[which][:7, ::, ::, ::]
for j in range(16):
new_pos = seq.predict(track[np.newaxis, ::, ::, ::, ::])
new = new_pos[::, -1, ::, ::, ::]
track = np.concatenate((track, new), axis=0)
# And then compare the predictions
# to the ground truth
track2 = noisy_movies[which][::, ::, ::, ::]
for i in range(15):
fig = plt.figure(figsize=(10, 5))
ax = fig.add_subplot(121)
if i >= 7:
ax.text(1, 3, 'Predictions !', fontsize=20, color='w')
else:
ax.text(1, 3, 'Initial trajectory', fontsize=20)
toplot = track[i, ::, ::, 0]
plt.imshow(toplot)
ax = fig.add_subplot(122)
plt.text(1, 3, 'Ground truth', fontsize=20)
toplot = track2[i, ::, ::, 0]
if i >= 2:
toplot = shifted_movies[which][i - 1, ::, ::, 0]
plt.imshow(toplot)
plt.savefig('%i_animate.png' % (i + 1))
'''
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】凌霞软件回馈社区,博客园 & 1Panel & Halo 联合会员上线
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】博客园社区专享云产品让利特惠,阿里云新客6.5折上折
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步
· 一个奇形怪状的面试题:Bean中的CHM要不要加volatile?
· [.NET]调用本地 Deepseek 模型
· 一个费力不讨好的项目,让我损失了近一半的绩效!
· .NET Core 托管堆内存泄露/CPU异常的常见思路
· PostgreSQL 和 SQL Server 在统计信息维护中的关键差异
· DeepSeek “源神”启动!「GitHub 热点速览」
· 微软正式发布.NET 10 Preview 1:开启下一代开发框架新篇章
· 我与微信审核的“相爱相杀”看个人小程序副业
· C# 集成 DeepSeek 模型实现 AI 私有化(本地部署与 API 调用教程)
· spring官宣接入deepseek,真的太香了~