CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In
huggingface

Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place. Commercial Alternative to JupyterHub.

GitHub Repository: huggingface/notebooks
 Path: blob/main/course/ja/chapter2/section2_tf.ipynb
Views: 2555
Kernel: Unknown Kernel

pipelineの裏側 (TensorFlow)

Install the Transformers, Datasets, and Evaluate libraries to run this notebook.

!pip install datasets evaluate transformers[sentencepiece]

from transformers import pipeline

classifier = pipeline("sentiment-analysis")
classifier(
    [
        "I've been waiting for a HuggingFace course my whole life.",
        "I hate this so much!",
    ]
)
[{'label': 'POSITIVE', 'score': 0.9598047137260437}, {'label': 'NEGATIVE', 'score': 0.9994558095932007}]
from transformers import AutoTokenizer

checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)

raw_inputs = [
    "I've been waiting for a HuggingFace course my whole life.",
    "I hate this so much!",
]
inputs = tokenizer(raw_inputs, padding=True, truncation=True, return_tensors="tf")
print(inputs)
{ 'input_ids': <tf.Tensor: shape=(2, 16), dtype=int32, numpy= array([ [ 101, 1045, 1005, 2310, 2042, 3403, 2005, 1037, 17662, 12172, 2607, 2026, 2878, 2166, 1012, 102], [ 101, 1045, 5223, 2023, 2061, 2172, 999, 102, 0, 0, 0, 0, 0, 0, 0, 0] ], dtype=int32)>, 'attention_mask': <tf.Tensor: shape=(2, 16), dtype=int32, numpy= array([ [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0] ], dtype=int32)> }
from transformers import TFAutoModel

checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
model = TFAutoModel.from_pretrained(checkpoint)

outputs = model(inputs)
print(outputs.last_hidden_state.shape)
(2, 16, 768)
from transformers import TFAutoModelForSequenceClassification

checkpoint = "distilbert-base-uncased-finetuned-sst-2-english"
model = TFAutoModelForSequenceClassification.from_pretrained(checkpoint)
outputs = model(inputs)

print(outputs.logits.shape)
(2, 2)
print(outputs.logits)
<tf.Tensor: shape=(2, 2), dtype=float32, numpy= array([[-1.5606991, 1.6122842], [ 4.169231 , -3.3464472]], dtype=float32)>
import tensorflow as tf

predictions = tf.math.softmax(outputs.logits, axis=-1)
print(predictions)
tf.Tensor( [[4.01951671e-02 9.59804833e-01] [9.9945587e-01 5.4418424e-04]], shape=(2, 2), dtype=float32)
model.config.id2label
{0: 'NEGATIVE', 1: 'POSITIVE'}