pip install transformers datasets accelerate tensorboard evaluate trackio --upgrade

from datasets import load_dataset

dataset = load_dataset("AI-Lab-Makerere/beans")

from transformers import AutoImageProcessor
teacher_processor = AutoImageProcessor.from_pretrained("merve/beans-vit-224")

def process(examples):
    processed_inputs = teacher_processor(examples["image"])
    return processed_inputs

processed_datasets = dataset.map(process, batched=True)

from transformers import TrainingArguments, Trainer
from accelerate import Accelerator
import torch
import torch.nn as nn
import torch.nn.functional as F

class ImageDistilTrainer(Trainer):
    def __init__(self, teacher_model=None, student_model=None, temperature=None, lambda_param=None,  *args, **kwargs):
        super().__init__(model=student_model, *args, **kwargs)
        self.teacher = teacher_model
        self.student = student_model
        self.loss_function = nn.KLDivLoss(reduction="batchmean")
        device = Accelerator().device
        self.teacher.to(device)
        self.teacher.eval()
        self.temperature = temperature
        self.lambda_param = lambda_param

    def compute_loss(self, student, inputs, return_outputs=False):
        student_output = self.student(**inputs)

        with torch.no_grad():
          teacher_output = self.teacher(**inputs)

        # Compute soft targets for teacher and student
        soft_teacher = F.softmax(teacher_output.logits / self.temperature, dim=-1)
        soft_student = F.log_softmax(student_output.logits / self.temperature, dim=-1)

        # Compute the loss
        distillation_loss = self.loss_function(soft_student, soft_teacher) * (self.temperature ** 2)

        # Compute the true label loss
        student_target_loss = student_output.loss

        # Calculate final loss
        loss = (1. - self.lambda_param) * student_target_loss + self.lambda_param * distillation_loss
        return (loss, student_output) if return_outputs else loss

from huggingface_hub import notebook_login

notebook_login()

from transformers import AutoModelForImageClassification, MobileNetV2Config, MobileNetV2ForImageClassification

training_args = TrainingArguments(
    output_dir="my-awesome-model",
    num_train_epochs=30,
    fp16=True,
    logging_strategy="epoch",
    eval_strategy="epoch",
    save_strategy="epoch",
    load_best_model_at_end=True,
    metric_for_best_model="accuracy",
    push_to_hub=True,
    hub_strategy="every_save",
    hub_model_id=repo_name,
    report_to="trackio",
    run_name="distillation",
    )

num_labels = len(processed_datasets["train"].features["labels"].names)

# initialize models
teacher_model = AutoModelForImageClassification.from_pretrained(
    "merve/beans-vit-224",
    num_labels=num_labels,
    ignore_mismatched_sizes=True
)

# training MobileNetV2 from scratch
student_config = MobileNetV2Config()
student_config.num_labels = num_labels
student_model = MobileNetV2ForImageClassification(student_config)

import evaluate
import numpy as np

accuracy = evaluate.load("accuracy")

def compute_metrics(eval_pred):
    predictions, labels = eval_pred
    acc = accuracy.compute(references=labels, predictions=np.argmax(predictions, axis=1))
    return {"accuracy": acc["accuracy"]}

from transformers import DefaultDataCollator

data_collator = DefaultDataCollator()
trainer = ImageDistilTrainer(
    student_model=student_model,
    teacher_model=teacher_model,
    training_args=training_args,
    train_dataset=processed_datasets["train"],
    eval_dataset=processed_datasets["validation"],
    data_collator=data_collator,
    processing_class=teacher_processor,
    compute_metrics=compute_metrics,
    temperature=5,
    lambda_param=0.5
)

trainer.train()

trainer.evaluate(processed_datasets["test"])