Create app.py

app.py

@@ -0,0 +1,159 @@
+import subprocess
+
+# Install the required packages
+subprocess.check_call(["pip", "install", "--upgrade", "pip"])
+subprocess.check_call(["pip", "install", "-U", "transformers"])
+subprocess.check_call(["pip", "install", "-U", "accelerate"])
+subprocess.check_call(["pip", "install", "datasets"])
+subprocess.check_call(["pip", "install", "evaluate"])
+subprocess.check_call(["pip", "install", "scikit-learn"])
+subprocess.check_call(["pip", "install", "torchvision"])
+
+model_checkpoint = "google/vit-base-patch16-224-in21k"
+batch_size = 128
+
+from datasets import load_dataset
+from evaluate import load
+
+metric = load("accuracy")
+
+# Load the dataset directly from Hugging Face
+dataset = load_dataset("DamarJati/Face-Mask-Detection")
+labels = dataset["train"].features["label"].names
+label2id, id2label = dict(), dict()
+for i, label in enumerate(labels):
+    label2id[label] = i
+    id2label[i] = label
+
+from transformers import AutoImageProcessor
+image_processor  = AutoImageProcessor.from_pretrained(model_checkpoint)
+image_processor
+
+from torchvision.transforms import (
+    CenterCrop,
+    Compose,
+    Normalize,
+    RandomHorizontalFlip,
+    RandomResizedCrop,
+    Resize,
+    ToTensor,
+    ColorJitter,
+    RandomRotation
+)
+
+normalize = Normalize(mean=image_processor.image_mean, std=image_processor.image_std)
+size = (image_processor.size["height"], image_processor.size["width"])
+
+train_transforms = Compose(
+        [
+            RandomResizedCrop(size),
+            RandomHorizontalFlip(),
+            RandomRotation(degrees=15),
+            ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4, hue=0.1),
+            ToTensor(),
+            normalize,
+        ]
+    )
+
+val_transforms = Compose(
+        [
+            Resize(size),
+            CenterCrop(size),
+            RandomRotation(degrees=15),
+            ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4, hue=0.1),
+            ToTensor(),
+            normalize,
+        ]
+    )
+
+def preprocess_train(example_batch):
+    example_batch["pixel_values"] = [
+        train_transforms(image.convert("RGB")) for image in example_batch["image"]
+    ]
+    return example_batch
+
+def preprocess_val(example_batch):
+    example_batch["pixel_values"] = [val_transforms(image.convert("RGB")) for image in example_batch["image"]]
+    return example_batch
+
+splits = dataset["train"].train_test_split(test_size=0.3)
+train_ds = splits['train']
+val_ds = splits['test']
+
+train_ds.set_transform(preprocess_train)
+val_ds.set_transform(preprocess_val)
+
+from transformers import AutoModelForImageClassification, TrainingArguments, Trainer
+
+model = AutoModelForImageClassification.from_pretrained(model_checkpoint,
+                                                        label2id=label2id,
+                                                        id2label=id2label,
+                                                        ignore_mismatched_sizes=True)
+
+model_name = model_checkpoint.split("/")[-1]
+
+args = TrainingArguments(
+    f"{model_name}-finetuned",
+    remove_unused_columns=False,
+    eval_strategy="epoch",  # Updated parameter
+    save_strategy="epoch",
+    save_total_limit=5,
+    learning_rate=1e-3,
+    per_device_train_batch_size=batch_size,
+    gradient_accumulation_steps=2,
+    per_device_eval_batch_size=batch_size,
+    num_train_epochs=2,
+    warmup_ratio=0.1,
+    weight_decay=0.01,
+    lr_scheduler_type="cosine",
+    logging_steps=10,
+    load_best_model_at_end=True,
+    metric_for_best_model="accuracy",
+)
+
+import numpy as np
+
+def compute_metrics(eval_pred):
+    """Computes accuracy on a batch of predictions"""
+    predictions = np.argmax(eval_pred.predictions, axis=1)
+    return metric.compute(predictions=predictions, references=eval_pred.label_ids)
+
+import torch
+
+def collate_fn(examples):
+    pixel_values = torch.stack([example["pixel_values"] for example in examples])
+    labels = torch.tensor([example["label"] for example in examples])
+    return {"pixel_values": pixel_values, "labels": labels}
+
+trainer = Trainer(
+    model=model,
+    args=args,
+    train_dataset=train_ds,
+    eval_dataset=val_ds,
+    tokenizer=image_processor,
+    compute_metrics=compute_metrics,
+    data_collator=collate_fn,
+)
+
+print("Starting training...")
+train_results = trainer.train()
+print("Training completed.")
+
+# Save model
+trainer.save_model()
+trainer.log_metrics("train", train_results.metrics)
+trainer.save_metrics("train", train_results.metrics)
+trainer.save_state()
+
+print("Starting evaluation...")
+metrics = trainer.evaluate()
+print("Evaluation completed.")
+
+# Log and save metrics
+trainer.log_metrics("eval", metrics)
+trainer.save_metrics("eval", metrics)
+
+# Print evaluation metrics
+print("Evaluation Metrics:")
+for key, value in metrics.items():
+    print(f"{key}: {value}")