ckeras.engine.sequential
Sequential
q )q}q(X _is_groupqX
keras_versionqC2.3.1qX backendqC
tensorflowqX model_configqB {"class_name": "Sequential", "config": {"name": "sequential_1", "layers": [{"class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "batch_input_shape": [null, 1], "dtype": "float32", "units": 50, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Dense", "config": {"name": "dense_2", "trainable": true, "dtype": "float32", "units": 50, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Dense", "config": {"name": "dense_3", "trainable": true, "dtype": "float32", "units": 1, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}]}}q X
model_weightsq
}q(hX layer_namesq]q
(Cdense_1qCdense_2qCdense_3qehC
tensorflowqhC2.3.1qX dense_1q}q(hX weight_namesq]q(Cdense_1/kernel:0qCdense_1/bias:0qeX dense_1/kernel:0qBe cnumpy.core.multiarray
_reconstruct
q cnumpy
ndarray
qK
qCbqqRq(KKK2qcnumpy
dtype
qX f4qK Kq Rq
(KX <qNNNJÿÿÿÿJÿÿÿÿK tqbCÈHôÙ¾v >ñ¾´cp¾c¾`A¦¾#è½Æö½ëHÓ>Ó>Ò ?ø!¾/¾é¸¾£¾dÊ>5¾oa¾c¾r¼ò>¾¶f¾÷>À{£¾¦ìÂ>kë½-·¾ä,¾n»_¡£¾þ X>ÐÑ»Y<¾Dk<DÉ>*I¾2ØH>®³¾:N¾©«>`0Ò¾ÞÑÚ½
¹¾Är>Uï>\Hs>ÒÉ>Ö ¾PSS¾'Gؾq
tqb.qX _dense_1/kernel:0_pickledqX dense_1/bias:0qBc cnumpy.core.multiarray
_reconstruct
q cnumpy
ndarray
qK
qCbqqRq(KK2
qcnumpy
dtype
qX f4qK Kq Rq
(KX <qNNNJÿÿÿÿJÿÿÿÿK tqbCÈÈøH¾Hq¿,¼H¾¼¥¾ÉÄ6¾4.¾`¦¾×Ù¾Y?°¾m¾·zO¾·`û¾µ4p¾ô¾Íkž$;#¼ISQ¾ Vs¾Éؽo¾>ؽcÁ¾Ã¾<ë,¾¶¾î¾¾µÄ`¾¾Ä¾Uß¼÷é¾û¾»½¨°n¾Ù½5¼Q¾,D
¾xv¿B¾î¾IY¾Ò`¾û½¤¾Ð½2Ã<¾Ù½5°f>ËY½¹öO¾á§¾Z©¯¼q
tqb.qX _dense_1/bias:0_pickledquX dense_2q}q (hh]q!(Cdense_2/kernel:0q"Cdense_2/bias:0q#eX dense_2/kernel:0q$B°' cnumpy.core.multiarray
_reconstruct
q cnumpy
ndarray
qK
qCbqqRq(KK2K2qcnumpy
dtype
qX f4qK Kq Rq
(KX <qNNNJÿÿÿÿJÿÿÿÿK tqbB' ¬½ê£p>¯}þ»=Ôéá½³sF½Üc>´Î½¡Ô½rª=ÉÊ_=C¢>õÓ
>(Gº
ú½¼v;:\;>Hâ=îã">xº=gK=îS3>J>
=¤2¾âSѽ6BÀ=T¤½ü³ç½B´¾ð½Wu]¾äõ>qo>¶)y>N+>~j&>\Q">[gï=u$¾4±j>0-¾¨fZ¾ñ=¶1=¾®¾B6M>Ö\$>ª¾ôß7¾4¾½ý»4>ø¸<ñÀ¾§>AR@>
RF>ØF¾Xð=ÎR> VZ¾»8>Ä=À%>¢>Û=ì'û¾ç¨H¾\ó=9S¾K¾×5=Q¿½Dö>"ÉU¾që{>jl>JmÀ½Dm*½Û«/½:t>w²>§®¾{;=c{>v½½Ý¾õ¾Ý/3½!Ün>²êñ½Áf>e¾ì(¾ÚÚ=¹ô¾Ü½¼xH>³gM¾Õî>ð%<A¬ê=;Cî=×Ñ^½ð½°eW<c]T¾>ï>Åj>Þð=êåP>ð¥i>J,^>æôÏ=,Hn½
v½ZZ=k¿=È<f=óYù½
¾ð>ñ¾ø_½ò&,¾ôV8>â.>Ôûß½PU¾ìB>ø@º¾Q >>I½=²ÝÊ<7_¥>-9¾vî½! :¾-=ÛÄ=;2>áìU¾Ðô<áÅë=àtd½*÷ñ=mSļÀk¾´=ÐW:>Ü<o>f¥¾D~4=þ=êBÃ=WÑb¼R=»`çe¾Æ;%¾q»S½{½ÓÛl>,®¾Tù¾¼ïL¾£[¼A@>qq>jÇ=Ó®$>b`>ª<¿¬y¾+rX>>¢½mE¾ _¾¾ ¥¾ñ³>ñ4¿Â½>Î
¶>4;gß =÷¾½ï¾J²é¼µTV¾M
>èNF>ò·à=6ì=Ëí¾f7E¾Äâ¼qFþ=^|½´¨{=rA¾ÄÕ¡>ù´n¾`)½ Z9ø~¾õnÍ=yÿ=<¢>°É0¾%»WM>¬²=ïè
>¾Ã=MG¯=x>Y¡¾*Ý>¦|ýÏç¼¥ÿ=àôG¾õ»·¾ÙÜ,>Lù<½¥ë½ePg>E×¾ØÀ½rü¥¾Ì^;½p¯k=>wØ1>^>l>VØ=:÷j½ä¸@½Kó <x_<b ¾èû¾¡oï»Í>yJJ>µz]>*Z2¾ö#½F9»¬Àí½R˶½:ßÊ<h0>¥>ð<¸¢>Q>ó~/>ðáA¾Rõ/>G)>5>¥é§¾åaÔ½<M=þí¢=úêa>Où=d¾}s½=¯X>/c½_7;ÝÞX¾ø[û<¤F;¦É⽿\¾[PZ>^ i=p¬X>å<2½àõÔ=b·õ¼
sV>4`D¾+>¸Ó½DN>3j6¾B{= Û^½_0¾Î[ó=fQ
¾%=U¾Õì¬=|l=.×¾
e>ã·o=]rÕ¾} =>(e}>Ä<ì¦<ét½¿ÜJ¾¥8>©D>q°ý<8ʾ1NQ¾%Mk¾¨ì=þ¶#>¡>Ù
=0w/<g"_=f¹¾ëÇP½HLò<¾N%o¾1ã!>S@i¾¼V>lw>>OÞ>æÛÁ>¢~½ÄµV;âC¾ ¶&;AgS¾T ù½¢O>áa>^ýÝÞX¾I
D¾ln+¾!ܾÚǾ$e¾©"y=C>×á¬=£+u¾ÌÕ%¿L¥C¾$P¾¿Áß>Q¸=æ>Æi<¾×Ôr¾6z=Aù/>¬O¼£
>νv¿0>qH=!ç>àr¾Ðß<¢ï=4 /¾%V>
>Â0¾AE¾s¾_O¾ >p{¼·¾?k]K>Ó©>ô*=ÂM¾:¾LlÅ=ì"=sÐ>
>¼¬l=ÿÙ
>Ãþ°¾89¾ª¼Àܾ£>LÅ=^Çö=K*¾*%=þµ=¸Ñ?½+¾Ê®v>$ö½ sM>5
>g.= ,½=K½}§¼Y¯Ò=qĽó
¾º;>~=³=nV½Ë< >Uº¾7¸>eË>ï¾½×ú@¾$ô=pÕ>¨5>Õ÷¾hM»½!X">¼u¾°«/¾Hd=XÕ >Ö
½jô ¾è»é¼Ý½øËý½¼Ô=¤Ã½äë3½-À>O2>kúÇ>Våñ½
Y]¾³o½ºR
¾¤'3¾Àj»¤æú½4¦Î>£¹<7óM>Ç=.ê²;H2½Õ$e¾Tñh>Y>«h¾=·Ô=mĽ8¾½½Ö³=³¢N=ê=5=eCǾaem>;û/¾ª¾q2þ<lí<nü¹ª>õæ%¾bõ½+o>È=h¼Á
Ê=5ºººñø=¯&ö½¹û>zxѽfD¾½ábi>gO>}nx¾SË<}2=.ô¹¼zåm¾Ô¾ød¾¸#æ<ÿ"õ=Üz.=°<Ti>Úa¾I²=]¥n¾Oc¾®¾~]ë½1>s0><ù=ép©¼æ¾²Å¾ÎJ¾>a+>C¢Ê½¸>$¬¾'Q½ ¾²VÖ½$¾ËÊ>yð=å4Ê> }¾ï¢¾y>á¾ÿª¾ØÕ_¾
Ô»r@ƽCZ¾Ø¿Â>²õ =S>>Fù½!â><¦½Mb½Úzl¾Á4ýºW§&½(Oé=®
>dìÀ¼ø¾ùA<¾ò=¨=8Ã*>2øé=¨
½^/>
=ùͲ½
¿K<
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
深度学习的资料合集(迁移学习、卷积神经网络、多层感知器).zip 是一个综合性的学习资源包,专为深度学习领域的学习者设计。本资源包含了一系列关于深度学习核心概念和技术的教程、笔记和代码示例,涵盖了迁移学习、卷积神经网络(CNN)、多层感知器(MLP)等关键领域。这些资料不仅适合计算机科学、人工智能及相关专业的在校学生,也适用于希望深入了解深度学习并应用于实际问题的研究人员和工程师。通过本资源的学习,用户将能够掌握深度学习的基本理论,了解如何利用迁移学习优化模型性能,以及如何设计和实现卷积神经网络和多层感知器来解决复杂的数据分析和模式识别任务。总之,这是一份宝贵的学习资源,有助于提升个人在深度学习领域的知识和技能。
资源推荐
资源详情
资源评论
收起资源包目录
深度学习的资料合集(迁移学习、卷积神经网络、多层感知器).zip (2000个子文件)
transfer_data2.csv 1022B
transfer_data.csv 964B
task2-vgg16-ms-apples-checkpoint.ipynb 4.23MB
task2-vgg16-ms-apples.ipynb 4.23MB
task2-vgg16-ms-apples-Copy1-checkpoint.ipynb 3.19MB
transfer-rnn-checkpoint.ipynb 294KB
task1-transferlearning-checkpoint.ipynb 193KB
task1-transferlearning.ipynb 193KB
task1-transferlearning-Copy1-checkpoint.ipynb 147KB
Untitled-Copy1-checkpoint.ipynb 139KB
VGG16批量图片预处理.ipynb 38KB
transfer-checkpoint.ipynb 35KB
23.jpg 223KB
23.jpg 223KB
22.jpg 129KB
22.jpg 129KB
10.jpg 112KB
10.jpg 112KB
dog.jpg 95KB
18.jpg 76KB
18.jpg 76KB
17.jpg 75KB
17.jpg 75KB
15.jpg 69KB
15.jpg 69KB
24.jpg 69KB
24.jpg 69KB
dog.4835.jpg 69KB
dog.4769.jpg 65KB
dog.4353.jpg 63KB
dog.4677.jpg 63KB
dog.4266.jpg 62KB
dog.4025.jpg 62KB
dog.4719.jpg 62KB
dog.4200.jpg 62KB
dog.4894.jpg 61KB
dog.4133.jpg 59KB
dog.4905.jpg 59KB
dog.4497.jpg 57KB
dog.4826.jpg 57KB
dog.4946.jpg 56KB
13.jpg 55KB
13.jpg 55KB
dog.4389.jpg 54KB
dog.4192.jpg 54KB
dog.4614.jpg 53KB
dog.4037.jpg 53KB
dog.4874.jpg 53KB
dog.4627.jpg 53KB
dog.4742.jpg 52KB
dog.4821.jpg 52KB
dog.4747.jpg 52KB
dog.4313.jpg 52KB
dog.4697.jpg 52KB
dog.4449.jpg 52KB
dog.4737.jpg 52KB
dog.4891.jpg 51KB
dog.4480.jpg 51KB
6.jpg 51KB
dog.4158.jpg 50KB
dog.4045.jpg 50KB
dog.4445.jpg 50KB
dog.4563.jpg 49KB
dog.4202.jpg 49KB
dog.4735.jpg 48KB
dog.4713.jpg 48KB
dog.4918.jpg 48KB
dog.4656.jpg 47KB
dog.4586.jpg 47KB
dog.4997.jpg 47KB
11.jpg 47KB
11.jpg 47KB
dog.4539.jpg 47KB
dog.4568.jpg 47KB
dog.4055.jpg 46KB
dog.4065.jpg 46KB
cat.4001.jpg 46KB
dog.4504.jpg 46KB
dog.4451.jpg 46KB
dog.4604.jpg 46KB
dog.4410.jpg 46KB
dog.4326.jpg 45KB
dog.4012.jpg 45KB
dog.4679.jpg 45KB
dog.4524.jpg 45KB
cat.4624.jpg 45KB
dog.4673.jpg 45KB
dog.4062.jpg 44KB
dog.4717.jpg 44KB
dog.4728.jpg 44KB
dog.4885.jpg 44KB
dog.4360.jpg 44KB
dog.4303.jpg 44KB
cat.4512.jpg 44KB
dog.4867.jpg 44KB
dog.4242.jpg 44KB
dog.4352.jpg 43KB
dog.4602.jpg 43KB
dog.4371.jpg 43KB
dog.4415.jpg 43KB
共 2000 条
- 1
- 2
- 3
- 4
- 5
- 6
- 20