Keras - SourceTrail

Yakagadziriswa: maitiro ekurodha keras modhi ine tsika yekurasikirwa basa

Senyanzvi muPython programming uye Keras Deep Learning framework, ndinonzwisisa hukasha hunobatanidzwa mukurodha modhi, kunyanya kana modhi yako ichishandisa tsika yekurasikirwa. Ichi chinyorwa chinokutungamira kuti ungakunda sei matambudziko aya uye nekubudirira kurodha yako Keras modhi netsika kurasikirwa basa.

Keras, yakakwira-level neural network API, iri mushandisi-inoshamwaridzika uye modular, inokwanisa kumhanya pamusoro peTensorFlow kana Theano. Iyo inozivikanwa nekureruka kwayo uye nyore kushandisa. Nekudaro, kunyangwe iri nyore, kunzwisisa mamwe mabasa senge kurodha modhi ine tsika yekurasikirwa basa kunogona kuve kwakaoma.

Yakagadziriswa: mazita layers

Mazita emazita muchirevo chechinyorwa chino anoreva chimiro chesangano chinowanzo shandiswa mukukodha, kuita kuti macode awedzere kuverengeka, akarongeka uye ari nyore kunzwisisa. Mazita akaturikidzana anovandudzawo kugona mukuita kwekodhi nekuda kwekurongwa kwavo kwakarongeka. Kuti uwane kunzwisiswa kuzere kwemashandiro emazita masheji muPython, ngatinyure mumudzi wedambudziko.

Yakagadziriswa: kuronga neural network

Kuvaka neural network modhi inzvimbo inonakidza mukudzidza kwemichina, kunyanya muPython. Inopa yakakura chiyero chekuongorora, kufanotaura, uye otomatiki maitiro ekuita sarudzo. Tisati tanyura mune nitty-gritty yekuvaka chirongwa neural network, zvakakosha kuti tinzwisise kuti neural network chii. Yakanyanya sisitimu yealgorithms inobatisisa chimiro chehuropi hwemunhu, nekudaro ichigadzira artificial neural network iyo, kuburikidza nekuongorora maitiro inodudzira data rekunzwa, kutora pane nuances 'zvisingaonekwe' neiyo mbishi data, sezvinoita uropi hwedu.

Yakagadziriswa: adam optimizer keras yekudzidza mwero inoderedza

Chokwadi, ngatitange nenyaya yacho.

Mamodheru ekudzidza akadzama ave chinhu chakakosha chetekinoroji munguva yanhasi, uye akasiyana optimization algorithms saAdam Optimizer anoita basa rakakosha mukuita kwavo. Keras, ine simba uye iri nyore kushandisa yemahara yakavhurika sosi raibhurari yePython yekugadzira uye yekuongorora yakadzama modhi yekudzidza, inoputira inoshanda manhamba ekuverenga maraibhurari Theano uye TensorFlow.

Yakagadziriswa: keras.utils.plot_model inoramba ichindiudza kuti ndiise pydot uye graphviz

Keras iraibhurari ine simba uye inoshanda yekugadzira michina yekudzidza modhi, kunyanya kudzidza kwakadzama mienzaniso. Chimwe chezvimiro zvayo kuronga modhi yedu kuita dhiyagiramu kuti inzwisise zviri nyore uye kugadzirisa matambudziko. Dzimwe nguva kumhanya keras.utils.plot_model kunogona kukanda zvikanganiso zvichiratidza kushaikwa kwesoftware zvinodiwa, kunyanya pydot uye graphviz. Unotarisirwa kuisa ese ari maviri. Zvakadaro, kunyangwe mushure mekuamisa, unogona kuwana iwo meseji yekukanganisa. Izvi zvinokonzerwa nemakwara uye zvigadziriso zvigadziriso zvisina kuiswa zvakanaka. Nechinyorwa chino, tichafamba nepakati pekugadzirisa nyaya iyi.

Yakagadziriswa: keras.datasets hapana module

Keras.datasets iraibhurari yedata pre-processing uye muchina kudzidza muPython. Inosanganisira tsigiro yeakajairwa data mafomati, senge CSV, JSON, uye Excel mafaera, pamwe neyakajairwa dataset.

Yakagadziriswa: Default stride value

Tichifunga kuti unoda chinyorwa paPython nhanho muNumPy Arrays, heino chinyorwa chako:

Tisati tanyura mumusoro mune ruzivo rwematanho muPython, zvakakosha kuti titange tanzwisisa zvavari. Strides ipfungwa muPython iyo inosimudzira zvakanyanya kubata uye kubata kwearrays, kunyanya NumPy arrays.. Iyo inotipa kugona kubata nemazvo arrays pasina kudiwa kwekuwedzera ndangariro kana computational mari. Iko kukosha kwenhanho kunongedza kumatanho akatorwa nePython kana ichifamba nepakati. Zvino ngationgororei kuti tingashandisa sei chinhu ichi chakasiyana kugadzirisa matambudziko.

Yakagadziriswa: keyer%3A %27acc%27

Munyika yekugadzira komputa, kusangana nekukanganisa chinhu chinowanzoitika. Tora, semuenzaniso, iyo KeyError: 'acc' in Python. Kukanganisa uku kunowanzoitika kana kiyi chaiyo yatiri kuedza kuwana kubva muduramazwi isipo. Sezvineiwo, Python inopa mhinduro yakajeka yekubata nyaya dzakadai uye kudzivirira kodhi yako kubva pakuparara. Izvi zvinosanganisira kushandisa maitiro ekubata, kushandisa get() basa, kana kutarisa makiyi usati waawana. Nemaitiro akakodzera, kukanganisa uku kunogona kutarisirwa neunyanzvi.

Yakagadziriswa: parametric relu mu keras convolution layer

Parametric Rectified Linear Units, kana PReLU, inounza kuchinjika kuKeras convolution layer. Sezvinongoita fashoni inochinjika kukuchinja mafambiro, ndizvowo zvinogona kuita yako AI modhi. Iyi ficha inotora yakakurumbira Rectified Linear Unit (ReLU) shanda nhanho inoenderera mberi nekubvumira iyo yakashata mutserendende kuti udzidzwe kubva kune yekupinda data, pane kuramba yakagadziriswa. Mune mazwi anoshanda, izvi zvinoreva kuti nePRELU, ma AI ako modhi anogona kuburitsa uye kudzidza zvese zvakanaka uye zvisina kunaka maficha kubva kune yako yekuisa data, kuwedzera mashandiro avo uye kugona.