使用TensorFlow從頭開(kāi)始實(shí)現(xiàn)這個(gè)架構(gòu)
# 繪制模型
tf.keras.utils.plot_model(model, to_file='model.png', show_shapes=True, show_dtype=False,show_layer_names=True, rankdir='TB', expand_nested=False, dpi=96)
模型圖的一個(gè)片段:
使用TensorFlow的MobileNet模型實(shí)現(xiàn):
import tensorflow as tf
# 導(dǎo)入所有必要的層
from tensorflow.keras.layers import Input, DepthwiseConv2D
from tensorflow.keras.layers import Conv2D, BatchNormalization
from tensorflow.keras.layers import ReLU, AvgPool2D, Flatten, Dense
from tensorflow.keras import Model
# MobileNet block
def mobilnet_block (x, filters, strides):
x = DepthwiseConv2D(kernel_size = 3, strides = strides, padding = 'same')(x)
x = BatchNormalization()(x)
x = ReLU()(x)
x = Conv2D(filters = filters, kernel_size = 1, strides = 1)(x)
x = BatchNormalization()(x)
x = ReLU()(x)
return x
# 模型主干
input = Input(shape = (224,224,3))
x = Conv2D(filters = 32, kernel_size = 3, strides = 2, padding = 'same')(input)
x = BatchNormalization()(x)
x = ReLU()(x)
# 模型的主要部分
x = mobilnet_block(x, filters = 64, strides = 1)
x = mobilnet_block(x, filters = 128, strides = 2)
x = mobilnet_block(x, filters = 128, strides = 1)
x = mobilnet_block(x, filters = 256, strides = 2)
x = mobilnet_block(x, filters = 256, strides = 1)
x = mobilnet_block(x, filters = 512, strides = 2)
for _ in range (5):
x = mobilnet_block(x, filters = 512, strides = 1)
x = mobilnet_block(x, filters = 1024, strides = 2)
x = mobilnet_block(x, filters = 1024, strides = 1)
x = AvgPool2D (pool_size = 7, strides = 1, data_format='channels_first')(x)
output = Dense (units = 1000, activation = 'softmax')(x)
model = Model(inputs=input, outputs=output)
model.summary()
# 繪制模型
tf.keras.utils.plot_model(model, to_file='model.png', show_shapes=True, show_dtype=False,show_layer_names=True, rankdir='TB', expand_nested=False, dpi=96)
結(jié)論
MobileNet是最小的深度神經(jīng)網(wǎng)絡(luò)之一,它速度快、效率高,可以在沒(méi)有高端GPU的設(shè)備上運(yùn)行。
當(dāng)使用Keras(在TensorFlow上)這樣的框架時(shí),這些網(wǎng)絡(luò)的實(shí)現(xiàn)非常簡(jiǎn)單。

發(fā)表評(píng)論
請(qǐng)輸入評(píng)論內(nèi)容...
請(qǐng)輸入評(píng)論/評(píng)論長(zhǎng)度6~500個(gè)字
圖片新聞
-
機(jī)器人奧運(yùn)會(huì)戰(zhàn)報(bào):宇樹(shù)機(jī)器人摘下首金,天工Ultra搶走首位“百米飛人”
-
存儲(chǔ)圈掐架!江波龍起訴佰維,索賠121萬(wàn)
-
長(zhǎng)安汽車(chē)母公司突然更名:從“中國(guó)長(zhǎng)安”到“辰致科技”
-
豆包前負(fù)責(zé)人喬木出軌BP后續(xù):均被辭退
-
字節(jié)AI Lab負(fù)責(zé)人李航卸任后返聘,Seed進(jìn)入調(diào)整期
-
員工持股爆雷?廣汽埃安緊急回應(yīng)
-
中國(guó)“智造”背后的「關(guān)鍵力量」
-
小米汽車(chē)研發(fā)中心重磅落地,寶馬家門(mén)口“搶人”
最新活動(dòng)更多
-
10月23日火熱報(bào)名中>> 2025是德科技創(chuàng)新技術(shù)峰會(huì)
-
10月23日立即報(bào)名>> Works With 開(kāi)發(fā)者大會(huì)深圳站
-
10月24日立即參評(píng)>> 【評(píng)選】維科杯·OFweek 2025(第十屆)物聯(lián)網(wǎng)行業(yè)年度評(píng)選
-
11月27日立即報(bào)名>> 【工程師系列】汽車(chē)電子技術(shù)在線大會(huì)
-
12月18日立即報(bào)名>> 【線下會(huì)議】OFweek 2025(第十屆)物聯(lián)網(wǎng)產(chǎn)業(yè)大會(huì)
-
精彩回顧立即查看>> 【限時(shí)福利】TE 2025國(guó)際物聯(lián)網(wǎng)展·深圳站
推薦專(zhuān)題