pip install transformers datasets evaluate -q
pip install jiwer -q

from huggingface_hub import notebook_login

notebook_login()

from datasets import load_dataset

ds = load_dataset("lambdalabs/pokemon-blip-captions")
ds

DatasetDict({
    train: Dataset({
        features: ['image', 'text'],
        num_rows: 833
    })
})

ds = ds["train"].train_test_split(test_size=0.1)
train_ds = ds["train"]
test_ds = ds["test"]

from textwrap import wrap
import matplotlib.pyplot as plt
import numpy as np


def plot_images(images, captions):
    plt.figure(figsize=(20, 20))
    for i in range(len(images)):
        ax = plt.subplot(1, len(images), i + 1)
        caption = captions[i]
        caption = "\n".join(wrap(caption, 12))
        plt.title(caption)
        plt.imshow(images[i])
        plt.axis("off")


sample_images_to_visualize = [np.array(train_ds[i]["image"]) for i in range(5)]
sample_captions = [train_ds[i]["text"] for i in range(5)]
plot_images(sample_images_to_visualize, sample_captions)

from transformers import AutoProcessor

checkpoint = "microsoft/git-base"
processor = AutoProcessor.from_pretrained(checkpoint)

def transforms(example_batch):
    images = [x for x in example_batch["image"]]
    captions = [x for x in example_batch["text"]]
    inputs = processor(images=images, text=captions, padding="max_length")
    inputs.update({"labels": inputs["input_ids"]})
    return inputs


train_ds.set_transform(transforms)
test_ds.set_transform(transforms)

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(checkpoint)

from evaluate import load
import torch

wer = load("wer")


def compute_metrics(eval_pred):
    logits, labels = eval_pred
    predicted = logits.argmax(-1)
    decoded_labels = processor.batch_decode(labels, skip_special_tokens=True)
    decoded_predictions = processor.batch_decode(predicted, skip_special_tokens=True)
    wer_score = wer.compute(predictions=decoded_predictions, references=decoded_labels)
    return {"wer_score": wer_score}

from transformers import TrainingArguments, Trainer

model_name = checkpoint.split("/")[1]

training_args = TrainingArguments(
    output_dir=f"{model_name}-pokemon",
    learning_rate=5e-5,
    num_train_epochs=50,
    fp16=True,
    per_device_train_batch_size=32,
    per_device_eval_batch_size=32,
    gradient_accumulation_steps=2,
    save_total_limit=3,
    eval_strategy="steps",
    eval_steps=50,
    save_strategy="steps",
    save_steps=50,
    logging_steps=50,
    remove_unused_columns=False,
    push_to_hub=True,
    label_names=["labels"],
    load_best_model_at_end=True,
)

trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_ds,
    eval_dataset=test_ds,
    compute_metrics=compute_metrics,
)

trainer.train()

trainer.push_to_hub()

from PIL import Image
import requests

url = "https://huggingface.co/datasets/sayakpaul/sample-datasets/resolve/main/pokemon.png"
image = Image.open(requests.get(url, stream=True).raw)
image

from accelerate import Accelerator

device = Accelerator().device
inputs = processor(images=image, return_tensors="pt").to(device)
pixel_values = inputs.pixel_values

generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_caption)

a drawing of a pink and blue pokemon