武安市城乡建设局网站,天眼查企业查询赵宝荣,网站免费注册会员怎么做,舟山网站网站建设数据集 四种奥特曼图片_数据集-飞桨AI Studio星河社区 (baidu.com) 中间的隐藏层 已经使用参数的空间
Conv2D卷积层
ReLU激活层
MaxPool2D最大池化层
AdaptiveAvgPool2D自适应的平均池化
Linear全链接层
Dropout放置过拟合#xff0c;随机丢弃神经元 -----------------… 数据集 四种奥特曼图片_数据集-飞桨AI Studio星河社区 (baidu.com) 中间的隐藏层 已经使用参数的空间
Conv2D卷积层
ReLU激活层
MaxPool2D最大池化层
AdaptiveAvgPool2D自适应的平均池化
Linear全链接层
Dropout放置过拟合随机丢弃神经元 --------------------------------------------------------------------------------Layer (type) Input Shape Output Shape Param #
Conv2D-1 [[50, 3, 227, 227]] [50, 64, 227, 227] 1,792 ReLU-1 [[50, 64, 227, 227]] [50, 64, 227, 227] 0 Conv2D-2 [[50, 64, 227, 227]] [50, 64, 227, 227] 36,928 ReLU-2 [[50, 64, 227, 227]] [50, 64, 227, 227] 0 MaxPool2D-1 [[50, 64, 227, 227]] [50, 64, 113, 113] 0 Conv2D-3 [[50, 64, 113, 113]] [50, 128, 113, 113] 73,856 ReLU-3 [[50, 128, 113, 113]] [50, 128, 113, 113] 0 Conv2D-4 [[50, 128, 113, 113]] [50, 128, 113, 113] 147,584 ReLU-4 [[50, 128, 113, 113]] [50, 128, 113, 113] 0 MaxPool2D-2 [[50, 128, 113, 113]] [50, 128, 56, 56] 0 Conv2D-5 [[50, 128, 56, 56]] [50, 256, 56, 56] 295,168 ReLU-5 [[50, 256, 56, 56]] [50, 256, 56, 56] 0 Conv2D-6 [[50, 256, 56, 56]] [50, 256, 56, 56] 590,080 ReLU-6 [[50, 256, 56, 56]] [50, 256, 56, 56] 0 Conv2D-7 [[50, 256, 56, 56]] [50, 256, 56, 56] 590,080 ReLU-7 [[50, 256, 56, 56]] [50, 256, 56, 56] 0 MaxPool2D-3 [[50, 256, 56, 56]] [50, 256, 28, 28] 0 Conv2D-8 [[50, 256, 28, 28]] [50, 512, 28, 28] 1,180,160 ReLU-8 [[50, 512, 28, 28]] [50, 512, 28, 28] 0 Conv2D-9 [[50, 512, 28, 28]] [50, 512, 28, 28] 2,359,808 ReLU-9 [[50, 512, 28, 28]] [50, 512, 28, 28] 0 Conv2D-10 [[50, 512, 28, 28]] [50, 512, 28, 28] 2,359,808 ReLU-10 [[50, 512, 28, 28]] [50, 512, 28, 28] 0 MaxPool2D-4 [[50, 512, 28, 28]] [50, 512, 14, 14] 0 Conv2D-11 [[50, 512, 14, 14]] [50, 512, 14, 14] 2,359,808 ReLU-11 [[50, 512, 14, 14]] [50, 512, 14, 14] 0 Conv2D-12 [[50, 512, 14, 14]] [50, 512, 14, 14] 2,359,808 ReLU-12 [[50, 512, 14, 14]] [50, 512, 14, 14] 0 Conv2D-13 [[50, 512, 14, 14]] [50, 512, 14, 14] 2,359,808 ReLU-13 [[50, 512, 14, 14]] [50, 512, 14, 14] 0 MaxPool2D-5 [[50, 512, 14, 14]] [50, 512, 7, 7] 0
AdaptiveAvgPool2D-1 [[50, 512, 7, 7]] [50, 512, 7, 7] 0 Linear-1 [[50, 25088]] [50, 4096] 102,764,544 ReLU-14 [[50, 4096]] [50, 4096] 0 Dropout-1 [[50, 4096]] [50, 4096] 0 Linear-2 [[50, 4096]] [50, 4096] 16,781,312 ReLU-15 [[50, 4096]] [50, 4096] 0 Dropout-2 [[50, 4096]] [50, 4096] 0 Linear-3 [[50, 4096]] [50, 4] 16,388 Total params: 134,276,932
Trainable params: 134,276,932
Non-trainable params: 0
--------------------------------------------------------------------------------
Input size (MB): 29.49
Forward/backward pass size (MB): 11120.24
Params size (MB): 512.23
Estimated Total Size (MB): 11661.95
-------------------------------------------------------------------------------- 如果paddle还没配置的话建议去网上搜一下这里就不给链接了 用于训练模型的代码
import paddle
from paddle.io import Dataset,DataLoader
import os
from PIL import Image
import numpy as np
import paddle.vision.transforms as T
import matplotlib.pyplot as plt
from paddle.vision.datasets import DatasetFoldertransformsT.Compose([T.Resize([227,227]),T.RandomRotation(degrees[-10,10]),T.ColorJitter(0.4,0.4,0.4,0.4),T.ToTensor()])
datasetDatasetFolder(aoteman,extensions[.jpg],transformtransforms)
#使用paddle.io.random_split切分训练集和测试集
from paddle.io import random_split
train_sizeint(0.8*len(dataset))
test_sizelen(dataset)-train_size
train_dataset,test_datasetrandom_split(datasetdataset,lengths[train_size,test_size])
print(len(train_dataset),len(test_dataset))# plt.figure(figsize[3,3])
# for idx,data in enumerate(train_dataset):
# plt.subplot(3,3,idx1)
# imdata[0];labeldata[1]
# imim.reshape([224,224,3])
# plt.imshow(im)
# if idx19:
# break
# plt.show()print(dataset.class_to_idx)netpaddle.vision.models.vgg16(pretrainedTrue, num_classes4)
paddle.summary(net,(50,3,227,227))#网络配置
lr0.001
batch_size50
#预训练模型优化器 Adam优化器
opt paddle.optimizer.Adam(learning_ratelr,parametersnet.classifier.parameters())
#损失函数
loss_fnpaddle.nn.CrossEntropyLoss()
#训练模式
net.train()
modelpaddle.Model(net)
model.prepare(optimizeropt,lossloss_fn,metricspaddle.metric.Accuracy())
import time
vsdlpaddle.callbacks.VisualDL(log_dirvsdl/trainlogstr(time.time()))
# model.load(mymodel/vgg_aoteman)
# resmodel.predict()
model.fit(train_datatrain_dataset,eval_datatest_dataset, batch_sizebatch_size,epochs1, verbose1,shuffleTrue,callbacksvsdl)
model.save(mymodel/vgg_aoteman)
用于预测模型的代码
import mathimport paddle
import paddle.vision.transforms as Tfrom PIL import Image
from paddle.vision.datasets import DatasetFolder
import numpy as nptransforms T.Compose([T.Resize([227, 227]), T.ToTensor()])
# 使用paddle.io.random_split切分训练集和测试集img Image.open(aoteman/predict_demo.jpg)#输入图片
img.show()
img transforms(img)
img img.unsqueeze(0)start_index 0 # 开始切片的索引
end_index 3 # 结束切片的索引
axes [1] # 要切片的轴通道轴
img paddle.slice(img, axesaxes, starts[start_index], ends[end_index])net paddle.vision.models.vgg16(pretrainedTrue, num_classes4)
# 网络配置
lr 0.001
batch_size 50
# 预训练模型优化器 Adam优化器
opt paddle.optimizer.Adam(learning_ratelr, parametersnet.classifier.parameters())
# 损失函数
loss_fn paddle.nn.CrossEntropyLoss()
# 训练模式
net.train()
model paddle.Model(net)
model.prepare(optimizeropt, lossloss_fn, metricspaddle.metric.Accuracy())
import timevsdl paddle.callbacks.VisualDL(log_dirvsdl/trainlog str(time.time()))
model.load(mymodel/vgg_aoteman)# print(img)
res model.predict_batch(img)sum0
maxx-1000000
idx0
for i in range(4):# summath.exp(res[0][0][i])if res[0][0][i]maxx:maxxres[0][0][i]idxi# print(res[0][0][i])
# print(res)
# print(math.exp(res[0][0][idx])/sum*100,end%: )
if idx0:print(迪迦)
elif idx1:print(杰克)
elif idx2:print(赛文)
else:print(泰罗)
