Transformers 4.37 中文文档（十）（2）

import tensorflow as tf
model = tf.keras.Sequential(
    [tf.keras.layers.Dense(10, input_shape=(10,), activation="relu"), tf.keras.layers.Dense(5, activation="softmax")]
)

# Generate random inputs for the model.
batch_size = 16
input_vector_dim = 10
random_inputs = tf.random.normal((batch_size, input_vector_dim))
# Run a forward pass.
_ = model(random_inputs)

xla_fn = tf.function(model, jit_compile=True)
_ = xla_fn(random_inputs)

my_xla_fn = tf.function(model.my_xla_fn, jit_compile=True)

pip install transformers --upgrade

import tensorflow as tf
from transformers import AutoTokenizer, TFAutoModelForCausalLM
# Will error if the minimal version of Transformers is not installed.
from transformers.utils import check_min_version
check_min_version("4.21.0")
tokenizer = AutoTokenizer.from_pretrained("gpt2", padding_side="left", pad_token="</s>")
model = TFAutoModelForCausalLM.from_pretrained("gpt2")
input_string = ["TensorFlow is"]
# One line to create an XLA generation function
xla_generate = tf.function(model.generate, jit_compile=True)
tokenized_input = tokenizer(input_string, return_tensors="tf")
generated_tokens = xla_generate(**tokenized_input, num_beams=2)
decoded_text = tokenizer.decode(generated_tokens[0], skip_special_tokens=True)
print(f"Generated -- {decoded_text}")
# Generated -- TensorFlow is an open-source, open-source, distributed-source application # framework for the

import tensorflow as tf
from transformers import AutoTokenizer, TFAutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("gpt2", padding_side="left", pad_token="</s>")
model = TFAutoModelForCausalLM.from_pretrained("gpt2")
input_string = ["TensorFlow is"]
xla_generate = tf.function(model.generate, jit_compile=True)
# Here, we call the tokenizer with padding options.
tokenized_input = tokenizer(input_string, pad_to_multiple_of=8, padding=True, return_tensors="tf")
generated_tokens = xla_generate(**tokenized_input, num_beams=2)
decoded_text = tokenizer.decode(generated_tokens[0], skip_special_tokens=True)
print(f"Generated -- {decoded_text}")

import time
import tensorflow as tf
from transformers import AutoTokenizer, TFAutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("gpt2", padding_side="left", pad_token="</s>")
model = TFAutoModelForCausalLM.from_pretrained("gpt2")
xla_generate = tf.function(model.generate, jit_compile=True)
for input_string in ["TensorFlow is", "TensorFlow is a", "TFLite is a"]:
    tokenized_input = tokenizer(input_string, pad_to_multiple_of=8, padding=True, return_tensors="tf")
    start = time.time_ns()
    generated_tokens = xla_generate(**tokenized_input, num_beams=2)
    end = time.time_ns()
    print(f"Execution time -- {(end - start) / 1e6:.1f} ms\n")

Execution time -- 30819.6 ms
Execution time -- 79.0 ms
Execution time -- 78.9 ms

from transformers import AutoModelForImageClassification
model = AutoModelForImageClassification.from_pretrained(MODEL_ID).to("cuda")
+ model = torch.compile(model)

import torch
from PIL import Image
import requests
import numpy as np
from transformers import AutoImageProcessor, AutoModelForImageClassification
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")
model = AutoModelForImageClassification.from_pretrained("google/vit-base-patch16-224").to("cuda")
model = torch.compile(model)
processed_input = processor(image, return_tensors='pt').to(device="cuda")
with torch.no_grad():
    _ = model(**processed_input)

from transformers import AutoImageProcessor, AutoModelForObjectDetection
processor = AutoImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = AutoModelForObjectDetection.from_pretrained("facebook/detr-resnet-50").to("cuda")
model = torch.compile(model)
texts = ["a photo of a cat", "a photo of a dog"]
inputs = processor(text=texts, images=image, return_tensors="pt").to("cuda")
with torch.no_grad():
    _ = model(**inputs)

from transformers import SegformerImageProcessor, SegformerForSemanticSegmentation
processor = SegformerImageProcessor.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512")
model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-ade-512-512").to("cuda")
model = torch.compile(model)
seg_inputs = processor(images=image, return_tensors="pt").to("cuda")
with torch.no_grad():
    _ = model(**seg_inputs)