Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / course /pr_1069 /rum /chapter3 /3_tf.html
rtrm's picture
rtrm
download
raw
42.5 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Ajustarea unui model cu Keras&quot;,&quot;local&quot;:&quot;ajustarea-unui-model-cu-keras&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Antrenarea&quot;,&quot;local&quot;:&quot;antrenarea&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Îmbunătățirea performanțelor de instruire&quot;,&quot;local&quot;:&quot;Îmbunătățirea-performanțelor-de-instruire&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Predicțiile modelului&quot;,&quot;local&quot;:&quot;predicțiile-modelului&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:1}">
 <link href="/docs/course/pr_1069/rum/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/entry/start.1de7c3d2.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/scheduler.37c15a92.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/singletons.e13b7dfd.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/index.18351ede.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/paths.e130b7b0.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/entry/app.1f82014c.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/index.2bf4358c.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/nodes/0.3c83e1ab.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/nodes/47.d83d1a18.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/Tip.363c041f.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/Youtube.1e50a667.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/CodeBlock.4e987730.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/CourseFloatingBanner.6add7356.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/FrameworkSwitchCourse.8d4d4ab6.js">
 <link rel="modulepreload" href="/docs/course/pr_1069/rum/_app/immutable/chunks/getInferenceSnippets.24b50994.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Ajustarea unui model cu Keras&quot;,&quot;local&quot;:&quot;ajustarea-unui-model-cu-keras&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Antrenarea&quot;,&quot;local&quot;:&quot;antrenarea&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Îmbunătățirea performanțelor de instruire&quot;,&quot;local&quot;:&quot;Îmbunătățirea-performanțelor-de-instruire&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Predicțiile modelului&quot;,&quot;local&quot;:&quot;predicțiile-modelului&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="bg-white leading-none border border-gray-100 rounded-lg flex p-0.5 w-56 text-sm mb-4"><a class="flex justify-center flex-1 py-1.5 px-2.5 focus:outline-none !no-underline rounded-l bg-red-50 dark:bg-transparent text-red-600" href="?fw=pt"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><defs><clipPath id="a"><rect x="3.05" y="0.5" width="25.73" height="31" fill="none"></rect></clipPath></defs><g clip-path="url(#a)"><path d="M24.94,9.51a12.81,12.81,0,0,1,0,18.16,12.68,12.68,0,0,1-18,0,12.81,12.81,0,0,1,0-18.16l9-9V5l-.84.83-6,6a9.58,9.58,0,1,0,13.55,0ZM20.44,9a1.68,1.68,0,1,1,1.67-1.67A1.68,1.68,0,0,1,20.44,9Z" fill="#ee4c2c"></path></g></svg> Pytorch </a><a class="flex justify-center flex-1 py-1.5 px-2.5 focus:outline-none !no-underline rounded-r text-gray-500 filter grayscale" href="?fw=tf"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="0.94em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 274"><path d="M145.726 42.065v42.07l72.861 42.07v-42.07l-72.86-42.07zM0 84.135v42.07l36.43 21.03V105.17L0 84.135zm109.291 21.035l-36.43 21.034v126.2l36.43 21.035v-84.135l36.435 21.035v-42.07l-36.435-21.034V105.17z" fill="#E55B2D"></path><path d="M145.726 42.065L36.43 105.17v42.065l72.861-42.065v42.065l36.435-21.03v-84.14zM255.022 63.1l-36.435 21.035v42.07l36.435-21.035V63.1zm-72.865 84.135l-36.43 21.035v42.07l36.43-21.036v-42.07zm-36.43 63.104l-36.436-21.035v84.135l36.435-21.035V210.34z" fill="#ED8E24"></path><path d="M145.726 0L0 84.135l36.43 21.035l109.296-63.105l72.861 42.07L255.022 63.1L145.726 0zm0 126.204l-36.435 21.03l36.435 21.036l36.43-21.035l-36.43-21.03z" fill="#F8BF3C"></path></svg> TensorFlow </a></div> <h1 class="relative group"><a id="ajustarea-unui-model-cu-keras" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#ajustarea-unui-model-cu-keras"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Ajustarea unui model cu Keras</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0"><a href="https://discuss.huggingface.co/t/chapter-3-questions" target="_blank"><img alt="Ask a Question" class="!m-0" src="https://img.shields.io/badge/Ask%20a%20question-ffcb4c.svg?logo=data:image/svg+xml;base64,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"></a> <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/en/chapter3/section3_tf.ipynb" target="_blank"><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/en/chapter3/section3_tf.ipynb" target="_blank"><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"></a></div> <p data-svelte-h="svelte-1tkd9sh">După ce ați efectuat toate lucrările de preprocesare a datelor din ultima secțiune, mai aveți doar câțiva pași de făcut pentru a antrena modelul. Rețineți, totuși, că comanda <code>model.fit()</code> va rula foarte lent pe un CPU. Dacă nu aveți un GPU configurat, puteți obține acces gratuit la GPU sau TPU pe <a href="https://colab.research.google.com/" rel="nofollow">Google Colab</a>.</p> <p data-svelte-h="svelte-1jxegwu">Exemplele de cod de mai jos presupun că ați executat deja exemplele din secțiunea anterioară. Iată un scurt rezumat care recapitulează ceea ce aveți nevoie:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, DataCollatorWithPadding
<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np
raw_datasets = load_dataset(<span class="hljs-string">&quot;glue&quot;</span>, <span class="hljs-string">&quot;mrpc&quot;</span>)
checkpoint = <span class="hljs-string">&quot;bert-base-uncased&quot;</span>
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
<span class="hljs-keyword">def</span> <span class="hljs-title function_">tokenize_function</span>(<span class="hljs-params">example</span>):
 <span class="hljs-keyword">return</span> tokenizer(example[<span class="hljs-string">&quot;sentence1&quot;</span>], example[<span class="hljs-string">&quot;sentence2&quot;</span>], truncation=<span class="hljs-literal">True</span>)
tokenized_datasets = raw_datasets.<span class="hljs-built_in">map</span>(tokenize_function, batched=<span class="hljs-literal">True</span>)
data_collator = DataCollatorWithPadding(tokenizer=tokenizer, return_tensors=<span class="hljs-string">&quot;tf&quot;</span>)
tf_train_dataset = tokenized_datasets[<span class="hljs-string">&quot;train&quot;</span>].to_tf_dataset(
 columns=[<span class="hljs-string">&quot;attention_mask&quot;</span>, <span class="hljs-string">&quot;input_ids&quot;</span>, <span class="hljs-string">&quot;token_type_ids&quot;</span>],
 label_cols=[<span class="hljs-string">&quot;labels&quot;</span>],
 shuffle=<span class="hljs-literal">True</span>,
 collate_fn=data_collator,
 batch_size=<span class="hljs-number">8</span>,
)
tf_validation_dataset = tokenized_datasets[<span class="hljs-string">&quot;validation&quot;</span>].to_tf_dataset(
 columns=[<span class="hljs-string">&quot;attention_mask&quot;</span>, <span class="hljs-string">&quot;input_ids&quot;</span>, <span class="hljs-string">&quot;token_type_ids&quot;</span>],
 label_cols=[<span class="hljs-string">&quot;labels&quot;</span>],
 shuffle=<span class="hljs-literal">False</span>,
 collate_fn=data_collator,
 batch_size=<span class="hljs-number">8</span>,
)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="antrenarea" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#antrenarea"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Antrenarea</span></h3> <p data-svelte-h="svelte-19o31yg">Modelele TensorFlow importate din 🤗 Transformers sunt deja modele Keras. În cele ce urmează găsiți o scurtă introducere în Keras.</p> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/rnTGBy2ax1c" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-16rugm9">Aceasta înseamnă că, odată ce avem datele noastre, este nevoie de foarte puțină muncă pentru a începe antrenarea pe baza acestora.</p> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/AUozVp78dhk" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-1me7yev">Ca și în <a href="/course/chapter2">capitolul anterior</a>, vom folosi clasa <code>TFAutoModelForSequenceClassification</code>, cu două etichete:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> TFAutoModelForSequenceClassification
model = TFAutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=<span class="hljs-number">2</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-7jyf30">Veți observa că, spre deosebire de <a href="/course/chapter2">Capitolul 2</a>, veți primi un avertisment după instanțierea acestui model preinstruit. Acest lucru se datorează faptului că BERT nu a fost preinstruit pentru clasificarea perechilor de propoziții, astfel încât head-ul modelului preinstruit a fost eliminat și a fost introdus în schimb un nou head adecvat pentru clasificarea secvențelor. Avertizările indică faptul că unele ponderi nu au fost utilizate (cele corespunzătoare head-ului de preformare eliminat) și că altele au fost inițializate aleatoriu (cele pentru noul head). În încheiere, vă încurajează să antrenați modelul, ceea ce vom face acum.</p> <p data-svelte-h="svelte-1wremft">Pentru a realiza fine-tuning-ul modelului pe setul nostru de date, trebuie doar să <code>compilăm()</code> modelul nostru și apoi să transmitem datele noastre metodei <code>fit()</code>. Aceasta va începe procesul de <code>fine-tuning</code> (care ar trebui să dureze câteva minute pe un GPU) și va raporta pierderea de formare pe parcurs, plus pierderea de validare la sfârșitul fiecărei epoci.</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-wozzu7">Rețineți că modelele 🤗 Transformers au o abilitate specială pe care majoritatea modelelor Keras nu o au - ele pot utiliza automat o valoare adecvată a pierderii pe care o calculează intern. Ele vor utiliza această valoare în mod implicit dacă nu setați un argument de pierdere în <code>compile()</code>. Rețineți că pentru a utiliza valoarea internă a pierderii va trebui să transmiteți etichetele ca parte a datelor de intrare, nu ca etichetă separată, care este modul normal de utilizare a etichetelor cu modelele Keras. Veți vedea exemple în acest sens în partea 2 a cursului, unde definirea funcției de pierdere corecte poate fi complicată. Cu toate acestea, pentru clasificarea secvențelor, o funcție de pierdere Keras standard funcționează bine, așa că aceasta este cea pe care o vom utiliza aici.</p></div> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tensorflow.keras.losses <span class="hljs-keyword">import</span> SparseCategoricalCrossentropy
model.<span class="hljs-built_in">compile</span>(
 optimizer=<span class="hljs-string">&quot;adam&quot;</span>,
 loss=SparseCategoricalCrossentropy(from_logits=<span class="hljs-literal">True</span>),
 metrics=[<span class="hljs-string">&quot;accuracy&quot;</span>],
)
model.fit(
 tf_train_dataset,
 validation_data=tf_validation_dataset,
)<!-- HTML_TAG_END --></pre></div> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-1n7baqr">Remarcați o problemă foarte des întâlnită aici - <em>puteți</em> doar să transmiteți numele pierderii ca șir de caractere către Keras, dar în mod implicit Keras va presupune că ați aplicat deja un softmax rezultatelor dvs. Cu toate acestea, multe modele produc valorile chiar înainte de aplicarea softmax, care sunt cunoscute și sub numele de <em>logits</em>. Trebuie să spunem funcției de pierdere că asta face modelul nostru, iar singura modalitate de a face acest lucru este să o apelăm direct, mai degrabă decât prin nume cu un șir.</p></div> <h3 class="relative group"><a id="Îmbunătățirea-performanțelor-de-instruire" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#Îmbunătățirea-performanțelor-de-instruire"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Îmbunătățirea performanțelor de instruire</span></h3> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/cpzq6ESSM5c" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-n9o7l8">Dacă încercați codul de mai sus, acesta rulează cu siguranță, dar veți constata că valoarea pierderii scade doar lent sau sporadic. Cauza principală
este <em>rata de învățare</em>. Ca și în cazul pierderii, atunci când îi transmitem lui Keras numele unui optimizator ca șir de caractere, Keras inițializează
optimizatorul respectiv cu valori implicite pentru toți parametrii, inclusiv rata de învățare. Totuși, din experiența îndelungată, știm
că modelele transformatoare beneficiază de o rată de învățare mult mai mică decât cea implicită pentru Adam, care este 1e-3, scrisă și
ca 10 la puterea -3, sau 0,001. 5e-5 (0,00005), care este de aproximativ douăzeci de ori mai mică, este un punct de plecare mult mai bun.</p> <p data-svelte-h="svelte-q19lx7">În plus față de scăderea ratei de învățare, avem un al doilea as în mânecă: putem reduce încet rata de învățare
pe parcursul instruirii. În literatura de specialitate, veți vedea uneori că acest lucru este denumit <em>decădere</em> sau <em>analizare</em>
a ratei de învățare. În Keras, cel mai bun mod de a face acest lucru este de a utiliza un <em>programator al ratei de învățare</em>. Un program bun de utilizat este
<code>PolynomialDecay</code> - în ciuda numelui, cu setările implicite, acesta pur și simplu scade liniar rata de învățare de la valoarea inițială
până la valoarea finală pe parcursul instruirii, ceea ce este exact ceea ce ne dorim. Pentru a utiliza corect un programator,
totuși, trebuie să îi spunem cât va dura antrenamentul. Calculăm acest lucru ca <code>num_train_steps</code> mai jos.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tensorflow.keras.optimizers.schedules <span class="hljs-keyword">import</span> PolynomialDecay
batch_size = <span class="hljs-number">8</span>
num_epochs = <span class="hljs-number">3</span>
<span class="hljs-comment"># Numărul etapelor de formare este numărul de eșantioane din setul de date, împărțit la dimensiunea batch-ului, apoi înmulțit</span>
<span class="hljs-comment"># cu numărul total de epoci. Rețineți că setul de date tf_train_dataset de aici este un set de date tf.data.Dataset în batch-uri,</span>
num_train_steps = <span class="hljs-built_in">len</span>(tf_train_dataset) * num_epochs
lr_scheduler = PolynomialDecay(
 initial_learning_rate=<span class="hljs-number">5e-5</span>, end_learning_rate=<span class="hljs-number">0.0</span>, decay_steps=num_train_steps
)
<span class="hljs-keyword">from</span> tensorflow.keras.optimizers <span class="hljs-keyword">import</span> Adam
opt = Adam(learning_rate=lr_scheduler)<!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-5r8p2s">Biblioteca Transformers 🤗 are, de asemenea, o funcție <code>create_optimizer()</code> care va crea un optimizator <code>AdamW</code> cu rata de învățare în scădere. Aceasta este o scurtătură convenabilă pe care o veți vedea în detaliu în secțiunile viitoare ale cursului.</p></div> <p data-svelte-h="svelte-7yyhhy">Acum avem optimizatorul nostru complet nou și putem încerca să ne antrenăm cu el. În primul rând, să reîncărcăm modelul, pentru a reseta modificările aduse ponderilor în urma instruirii pe care tocmai am efectuat-o, iar apoi îl putem compila cu noul optimizator:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> tensorflow <span class="hljs-keyword">as</span> tf
model = TFAutoModelForSequenceClassification.from_pretrained(checkpoint, num_labels=<span class="hljs-number">2</span>)
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=<span class="hljs-literal">True</span>)
model.<span class="hljs-built_in">compile</span>(optimizer=opt, loss=loss, metrics=[<span class="hljs-string">&quot;accuracy&quot;</span>])<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-157qypk">Acum, ne potrivim din nou:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->model.fit(tf_train_dataset, validation_data=tf_validation_dataset, epochs=<span class="hljs-number">3</span>)<!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-13frpsp">💡 Dacă doriți să încărcați automat modelul dvs. în Hub în timpul instruirii, puteți trece un <code>PushToHubCallback</code> în metoda <code>model.fit()</code>. Vom afla mai multe despre acest lucru în <a href="/course/chapter4/3">Capitolul 4</a></p></div> <h3 class="relative group"><a id="predicțiile-modelului" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#predicțiile-modelului"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Predicțiile modelului</span></h3> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/nx10eh4CoOs" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-11qehfc">Este foarte interesant să ne antrenăm și să vedem cum scade valoarea pierderii, dar ce se întâmplă dacă dorim să obținem rezultate de la modelul antrenat, fie pentru a calcula anumiți parametri, fie pentru a utiliza modelul în producție? Pentru a face acest lucru, putem folosi metoda <code>predict()</code>. Aceasta va returna <em>logit-urile</em> din rezultatele modelului, unul pentru fiecare clasă.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->preds = model.predict(tf_validation_dataset)[<span class="hljs-string">&quot;logits&quot;</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1khc15d">Putem converti aceste logiți în predicții de clasă ale modelului folosind <code>argmax</code> pentru a găsi cel mai mare logit, care corespunde celei mai probabile clase:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->class_preds = np.argmax(preds, axis=<span class="hljs-number">1</span>)
<span class="hljs-built_in">print</span>(preds.shape, class_preds.shape)<!-- HTML_TAG_END --></pre></div> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->(<span class="hljs-number">408</span>, <span class="hljs-number">2</span>) (<span class="hljs-number">408</span>,)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1rw7bk6">Acum, să folosim <code>preds</code> pentru a calcula niște indicatori! Putem încărca indicatorii de măsurare asociați cu setul de date MRPC la fel de ușor cum am încărcat setul de date, de data aceasta cu funcția <code>evaluate.load()</code>. Obiectul returnat are o metodă <code>compute()</code> pe care o putem folosi pentru a face calculul metric:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> evaluate
metric = evaluate.load(<span class="hljs-string">&quot;glue&quot;</span>, <span class="hljs-string">&quot;mrpc&quot;</span>)
metric.compute(predictions=class_preds, references=raw_datasets[<span class="hljs-string">&quot;validation&quot;</span>][<span class="hljs-string">&quot;label&quot;</span>])<!-- HTML_TAG_END --></pre></div> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->{<span class="hljs-string">&#x27;accuracy&#x27;</span>: <span class="hljs-number">0.8578431372549019</span>, <span class="hljs-string">&#x27;f1&#x27;</span>: <span class="hljs-number">0.8996539792387542</span>}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-mncsl2">Rezultatele exacte pe care le obțineți pot varia, deoarece inițializarea aleatorie a head-ului modelului poate schimba parametrii obținuți. Aici, putem vedea că modelul nostru are o precizie de 85,78% pe setul de validare și un scor F1 de 89,97. Acestea sunt cele două metrici utilizate pentru a evalua rezultatele pe setul de date MRPC pentru criteriul de referință GLUE. Tabelul din [lucrarea BERT] (<a href="https://arxiv.org/pdf/1810.04805.pdf" rel="nofollow">https://arxiv.org/pdf/1810.04805.pdf</a>) a raportat un scor F1 de 88,9 pentru modelul de bază. Acesta a fost modelul <code>uncased</code>, în timp ce noi folosim în prezent modelul <code>cased</code>, ceea ce explică rezultatul mai bun.</p> <p data-svelte-h="svelte-xejl6u">Aceasta încheie introducerea la ajustarea fină utilizând API-ul Keras. În <a href="/course/chapter7">Capitolul 7</a> va fi prezentat un exemplu de efectuare a acestui lucru pentru cele mai comune sarcini NLP. Dacă doriți să vă perfecționați abilitățile cu API-ul Keras, încercați să reglați un model pe setul de date GLUE SST-2, utilizând prelucrarea datelor pe care ați făcut-o în secțiunea 2.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/rum/chapter3/3_tf.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_1ftlxhy = {
 assets: "/docs/course/pr_1069/rum",
 base: "/docs/course/pr_1069/rum",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/course/pr_1069/rum/_app/immutable/entry/start.1de7c3d2.js"),
 import("/docs/course/pr_1069/rum/_app/immutable/entry/app.1f82014c.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 47],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
42.5 kB
·
Xet hash:
66401b838cbc3c4ca04555e7aa34dc75b6f42202059af11ac8a5593f746529e1

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.