Upload test1/Algo_CIFAR_100_convneXt.py with huggingface_hub

test1/Algo_CIFAR_100_convneXt.py

@@ -0,0 +1,254 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import Dataset, DataLoader
+import torchvision.transforms as transforms
+import torchvision.models as models
+from torchvision.models import ConvNeXt_Tiny_Weights
+from codecarbon import EmissionsTracker
+from carbontracker.tracker import CarbonTracker
+from fvcore.nn import FlopCountAnalysis
+from sklearn.metrics import precision_recall_fscore_support, accuracy_score
+from tqdm import tqdm
+import pandas as pd
+import numpy as np
+import pickle
+import os
+import time
+import logging
+import warnings
+import gc
+
+# --- Environment Optimization ---
+warnings.filterwarnings("ignore", category=UserWarning) 
+logging.getLogger("codecarbon").setLevel(logging.ERROR) 
+
+# --- Configurations ---
+DATA_DIR = r"C:\Users\shanm\Dataset Download\CIFAR100"
+LOG_FILE = "eden_unfrozen_cifar100_convnext.csv"
+MODEL_SAVE_PATH = "eden_unfrozen_convnext_cifar100.pth"
+
+BATCH_SIZE = 32
+ACCUMULATION_STEPS = 4
+LEARNING_RATE = 1e-3
+NUM_EPOCHS = 20
+UNFREEZE_EPOCH = 5      
+L1_LAMBDA = 1e-5        
+
+DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# --- Dataset Loader (RAM Cached for Binary CIFAR-100) ---
+class CIFAR100Binary(Dataset):
+    def __init__(self, root, train=True, transform=None):
+        file_name = 'train' if train else 'test'
+        file_path = os.path.join(root, file_name)
+        with open(file_path, 'rb') as f:
+            entry = pickle.load(f, encoding='latin1')
+            self.data = entry['data'].reshape(-1, 3, 32, 32).transpose(0, 2, 3, 1)
+            self.labels = entry['fine_labels']
+        self.transform = transform
+
+    def __len__(self): return len(self.data)
+    
+    def __getitem__(self, idx):
+        img, target = self.data[idx], self.labels[idx]
+        if self.transform: 
+            img = self.transform(img)
+        return img, target
+
+# --- Main Profiling Engine ---
+def run_experiment():
+    torch.cuda.empty_cache()
+    gc.collect()
+    
+    # --- 1. Pure PyTorch Transfer Learning Setup ---
+    print("\n[EDEN Phase 1] Loading Native PyTorch ConvNeXt-Tiny...")
+    
+    weights = ConvNeXt_Tiny_Weights.DEFAULT
+    model = models.convnext_tiny(weights=weights)
+    
+    # Freeze the ConvNeXt backbone initially
+    for param in model.features.parameters():
+        param.requires_grad = False
+        
+    # Isolate and unfreeze the classification head natively for 100 classes
+    in_features = model.classifier[2].in_features
+    model.classifier[2] = nn.Linear(in_features, 100) # Updated for CIFAR-100
+    
+    for param in model.classifier.parameters():
+        param.requires_grad = True
+
+    model = model.to(DEVICE)
+    optimizer = optim.Adam(model.classifier.parameters(), lr=LEARNING_RATE)
+
+    # Complexity Metrics (Static)
+    dummy_input = torch.randn(1, 3, 224, 224).to(DEVICE)
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore")
+        total_flops = FlopCountAnalysis(model, dummy_input).total()
+    total_params = sum(p.numel() for p in model.parameters())
+
+    transform = transforms.Compose([
+        transforms.ToPILImage(),
+        transforms.Resize(224),
+        transforms.ToTensor(),
+        transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
+    ])
+    
+    train_set = CIFAR100Binary(DATA_DIR, train=True, transform=transform)
+    loader = DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True, num_workers=4, pin_memory=True)
+
+    criterion = nn.CrossEntropyLoss()
+    scaler = torch.cuda.amp.GradScaler() 
+    
+    # --- 2. Trackers Initialization ---
+    cc_tracker = EmissionsTracker(measure_power_secs=1, save_to_file=False)
+    ct_tracker = CarbonTracker(epochs=NUM_EPOCHS, monitor_epochs=NUM_EPOCHS, update_interval=1)
+    
+    cc_tracker.start()
+    all_logs = []
+    total_iterations_counter = 0
+    session_start_time = time.time()
+
+    prev_cum_gpu_j, prev_cum_cpu_j, prev_cum_ram_j = 0.0, 0.0, 0.0
+    prev_acc = 0.0
+
+    print(f"\nEDEN PROFILING STARTED | DEVICE: {torch.cuda.get_device_name(0)}")
+    print(f"Dataset: CIFAR-100 | Architecture: ConvNeXt-Tiny")
+    print(f"Params: {total_params:,} | FLOPs: {total_flops:.2e}\n")
+
+    for epoch in range(NUM_EPOCHS):
+        # --- Stage 2: Progressive Unfreezing ---
+        if epoch + 1 == UNFREEZE_EPOCH:
+            print("\n[STAGE 2 INITIATED] Unfreezing ConvNeXt Backbone for Fine-Tuning...")
+            for param in model.parameters():
+                param.requires_grad = True
+            optimizer = optim.Adam(model.parameters(), lr=LEARNING_RATE * 0.1)
+
+        ct_tracker.epoch_start()
+        torch.cuda.reset_peak_memory_stats() 
+        epoch_start_time = time.time()
+        model.train()
+        
+        running_loss = 0.0
+        all_preds, all_labels = [], []
+        epoch_grad_norms = []
+        
+        optimizer.zero_grad()
+        pbar = tqdm(loader, desc=f"Epoch {epoch+1}/{NUM_EPOCHS}", unit="batch", leave=False)
+        
+        for i, (images, labels) in enumerate(pbar):
+            images, labels = images.to(DEVICE), labels.to(DEVICE)
+            
+            with torch.cuda.amp.autocast():
+                outputs = model(images)
+                loss = criterion(outputs, labels)
+                
+                # Active Sparse Training (L1 Penalty)
+                trainable_params = [p for p in model.parameters() if p.requires_grad]
+                l1_penalty = sum(p.abs().sum() for p in trainable_params)
+                
+                total_loss = loss + (L1_LAMBDA * l1_penalty)
+                scaled_loss = total_loss / ACCUMULATION_STEPS
+
+            scaler.scale(scaled_loss).backward()
+            
+            grad_norm = 0.0
+            for p in model.parameters():
+                if p.requires_grad and p.grad is not None:
+                    grad_norm += p.grad.data.norm(2).item() ** 2
+            epoch_grad_norms.append(grad_norm ** 0.5)
+
+            if (i + 1) % ACCUMULATION_STEPS == 0:
+                scaler.step(optimizer)
+                scaler.update()
+                optimizer.zero_grad()
+
+            running_loss += loss.item() * ACCUMULATION_STEPS
+            
+            _, preds = torch.max(outputs, 1)
+            all_preds.extend(preds.cpu().numpy())
+            all_labels.extend(labels.cpu().numpy())
+            total_iterations_counter += 1
+            
+            pbar.set_postfix(loss=f"{(loss.item()*ACCUMULATION_STEPS):.4f}")
+
+        # --- A. Evaluation ---
+        ct_tracker.epoch_end()
+        epoch_end_time = time.time()
+        epoch_duration = epoch_end_time - epoch_start_time
+        avg_it_per_sec = len(loader) / epoch_duration
+        
+        acc = accuracy_score(all_labels, all_preds)
+        p, r, f1, _ = precision_recall_fscore_support(all_labels, all_preds, average='macro', zero_division=0)
+        
+        # Rigorous Inference Latency (With Warm-up)
+        model.eval()
+        with torch.no_grad():
+            sample_img = torch.randn(1, 3, 224, 224).to(DEVICE)
+            _ = model(sample_img) 
+            torch.cuda.synchronize()
+            
+            starter, ender = torch.cuda.Event(enable_timing=True), torch.cuda.Event(enable_timing=True)
+            starter.record()
+            _ = model(sample_img) 
+            ender.record()
+            torch.cuda.synchronize()
+            lat_ms = starter.elapsed_time(ender)
+
+        # --- B. Energy & Power Calculations ---
+        emissions_data = cc_tracker._prepare_emissions_data()
+        
+        cum_gpu_j = emissions_data.gpu_energy * 3.6e6
+        cum_cpu_j = emissions_data.cpu_energy * 3.6e6
+        cum_ram_j = emissions_data.ram_energy * 3.6e6
+        cum_total_j = cum_gpu_j + cum_cpu_j + cum_ram_j
+        
+        epoch_gpu_j = cum_gpu_j - prev_cum_gpu_j
+        epoch_cpu_j = cum_cpu_j - prev_cum_cpu_j
+        epoch_ram_j = cum_ram_j - prev_cum_ram_j
+        epoch_total_j = epoch_gpu_j + epoch_cpu_j + epoch_ram_j
+        
+        prev_cum_gpu_j, prev_cum_cpu_j, prev_cum_ram_j = cum_gpu_j, cum_cpu_j, cum_ram_j
+
+        avg_gpu_w = epoch_gpu_j / epoch_duration if epoch_duration > 0 else 0
+        avg_cpu_w = epoch_cpu_j / epoch_duration if epoch_duration > 0 else 0
+        avg_ram_w = epoch_ram_j / epoch_duration if epoch_duration > 0 else 0
+
+        vram_peak = torch.cuda.max_memory_allocated(DEVICE) / (1024**3)
+        
+        acc_gain = acc - prev_acc
+        eag = acc_gain / epoch_total_j if epoch_total_j > 0 else 0
+        prev_acc = acc
+
+        # --- C. Terminal Update ---
+        print(f"Epoch {epoch+1} Summary:")
+        print(f" > Acc: {acc:.4f} | F1: {f1:.4f} | Loss: {running_loss/len(loader):.4f}")
+        print(f" > Epoch Energy: {epoch_total_j:.1f}J | EAG: {eag:.8f}")
+        print(f" > Avg Power: GPU {avg_gpu_w:.1f}W | VRAM: {vram_peak:.2f}GB | Latency: {lat_ms:.2f}ms")
+        print("-" * 65)
+
+        # --- D. Unified Verified CSV Logging ---
+        log_entry = {
+            "epoch": epoch + 1,
+            "loss": running_loss / len(loader),
+            "accuracy": acc, "f1_score": f1, "precision": p, "recall": r,
+            "epoch_energy_gpu_j": epoch_gpu_j, "epoch_energy_cpu_j": epoch_cpu_j,
+            "epoch_energy_ram_j": epoch_ram_j, "epoch_total_energy_j": epoch_total_j,
+            "cumulative_total_energy_j": cum_total_j, "carbon_emissions_kg": emissions_data.emissions,
+            "avg_power_gpu_w": avg_gpu_w, "avg_power_cpu_w": avg_cpu_w, "avg_power_ram_w": avg_ram_w,
+            "vram_peak_gb": vram_peak, "latency_ms": lat_ms, "avg_grad_norm": np.mean(epoch_grad_norms),
+            "eag_metric": eag, "it_per_sec": avg_it_per_sec, "total_iterations": total_iterations_counter,
+            "epoch_duration_sec": epoch_duration, "cumulative_time_sec": time.time() - session_start_time
+        }
+        all_logs.append(log_entry)
+        pd.DataFrame(all_logs).to_csv(LOG_FILE, index=False)
+
+    cc_tracker.stop()
+    
+    # --- E. Save Optimized Model ---
+    torch.save(model.state_dict(), MODEL_SAVE_PATH)
+    print(f"\n[FINISH] Verified Optimization Complete.")
+
+if __name__ == "__main__":
+    run_experiment()