Upload 2 files

imageAI.py

@@ -0,0 +1,319 @@
+try:
+  import google.colab
+  IN_COLAB = True
+  from google.colab import drive,files
+  from google.colab import output
+  drive.mount('/gdrive')
+  Gbase="/gdrive/MyDrive/generate/"
+  cache_dir="/gdrive/MyDrive/hf/"
+  import sys
+  sys.path.append(Gbase)
+except:
+  IN_COLAB = False
+  Gbase="./"
+  cache_dir="./hf/"
+
+
+import cv2,os
+import numpy as np
+import random,string
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+from torch.utils.data import Dataset, DataLoader
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+print(f"Using device: {device}")
+
+IMAGE_SIZE = 64
+NUM_SAMPLES = 1000
+BATCH_SIZE = 4
+EPOCHS = 500
+LEARNING_RATE = 0.001
+
+
+def generate_sample(num_shapes=1):
+    image = np.zeros((IMAGE_SIZE, IMAGE_SIZE), dtype=np.uint8)
+    instructions = []
+    
+    #num_shapes = random.randint(1, 3)
+    for _ in range(num_shapes):
+        shape = random.choice(['line', 'rectangle', 'circle', 'ellipse', 'polygon'])
+        color = random.randint(0, 255)
+        thickness = random.randint(1, 3)
+        
+        if shape == 'line':
+            start_point = (random.randint(0, IMAGE_SIZE), random.randint(0, IMAGE_SIZE))
+            end_point = (random.randint(0, IMAGE_SIZE), random.randint(0, IMAGE_SIZE))
+            cv2.line(image, start_point, end_point, color, thickness)
+            instructions.append(f"cv2.line(image, {start_point}, {end_point}, {color}, {thickness})")
+        
+        elif shape == 'rectangle':
+            start_point = (random.randint(0, IMAGE_SIZE - 10), random.randint(0, IMAGE_SIZE - 10))
+            end_point = (start_point[0] + random.randint(10, IMAGE_SIZE - start_point[0]),
+                         start_point[1] + random.randint(10, IMAGE_SIZE - start_point[1]))
+            cv2.rectangle(image, start_point, end_point, color, thickness)
+            instructions.append(f"cv2.rectangle(image, {start_point}, {end_point}, {color}, {thickness})")
+        
+        elif shape == 'circle':
+            center = (random.randint(10, IMAGE_SIZE - 10), random.randint(10, IMAGE_SIZE - 10))
+            radius = random.randint(5, min(center[0], center[1], IMAGE_SIZE - center[0], IMAGE_SIZE - center[1]))
+            cv2.circle(image, center, radius, color, thickness)
+            instructions.append(f"cv2.circle(image, {center}, {radius}, {color}, {thickness})")
+        
+        elif shape == 'ellipse':
+            center = (random.randint(10, IMAGE_SIZE - 10), random.randint(10, IMAGE_SIZE - 10))
+            axes = (random.randint(5, 30), random.randint(5, 30))
+            angle = random.randint(0, 360)
+            cv2.ellipse(image, center, axes, angle, 0, 360, color, thickness)
+            instructions.append(f"cv2.ellipse(image, {center}, {axes}, {angle}, 0, 360, {color}, {thickness})")
+        
+        elif shape == 'polygon':
+            num_points = random.randint(3, 6)
+            points = np.array([(random.randint(0, IMAGE_SIZE), random.randint(0, IMAGE_SIZE)) for _ in range(num_points)], np.int32)
+            points = points.reshape((-1, 1, 2))
+            cv2.polylines(image, [points], True, color, thickness)
+            instructions.append(f"cv2.polylines(image, [{points.tolist()}], True, {color}, {thickness})")
+        
+    return {'image': image, 'instructions': instructions}
+
+def generate_dataset(NUM_SAMPLES=NUM_SAMPLES,maxNumShape=3):
+    dataset = []
+    for _ in range(NUM_SAMPLES):
+        num_shapes = random.randint(1, maxNumShape)
+        sample = generate_sample(num_shapes=num_shapes)
+        dataset.append(sample)
+    return dataset
+
+class ImageDataset(Dataset):
+    def __init__(self, dataset):
+        self.dataset = dataset
+    
+    def __len__(self):
+        return len(self.dataset)
+    
+    def __getitem__(self, idx):
+        sample = self.dataset[idx]
+        image = torch.FloatTensor(sample['image']).unsqueeze(0) / 255.0
+        return image, len(sample['instructions'])
+
+class SimpleModel(nn.Module):
+    def __init__(self, path=None):
+        super(SimpleModel, self).__init__()
+        self.conv1 = nn.Conv2d(1, 32, 3, padding=1)
+        self.bn1 = nn.BatchNorm2d(32)
+        self.conv2 = nn.Conv2d(32, 64, 3, padding=1)
+        self.bn2 = nn.BatchNorm2d(64)
+        self.conv3 = nn.Conv2d(64, 128, 3, padding=1)
+        self.bn3 = nn.BatchNorm2d(128)
+        self.pool = nn.MaxPool2d(2, 2)
+        self.fc1 = nn.Linear(128 * 8 * 8, 512)
+        self.fc2 = nn.Linear(512, 128)
+        self.fc3 = nn.Linear(128, 1)
+        self.dropout = nn.Dropout(0.5)
+        
+        if path and os.path.exists(path):
+            self.load_state_dict(torch.load(path, map_location=device))
+    
+    def forward(self, x):
+        x = self.pool(F.leaky_relu(self.bn1(self.conv1(x))))
+        x = self.pool(F.leaky_relu(self.bn2(self.conv2(x))))
+        x = self.pool(F.leaky_relu(self.bn3(self.conv3(x))))
+        x = x.view(-1, 128 * 8 * 8)
+        x = F.leaky_relu(self.fc1(x))
+        x = self.dropout(x)
+        x = F.leaky_relu(self.fc2(x))
+        x = self.dropout(x)
+        x = self.fc3(x)
+        return x
+
+    def predict(self, image):
+        self.eval()
+        with torch.no_grad():
+            if isinstance(image, str) and os.path.isfile(image):
+                # 如果輸入是圖片文件路徑
+                img = cv2.imread(image, cv2.IMREAD_GRAYSCALE)
+                img = cv2.resize(img, (IMAGE_SIZE, IMAGE_SIZE))
+            elif isinstance(image, np.ndarray):
+                # 如果輸入是 numpy 數組
+                if image.ndim == 3:
+                    img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+                else:
+                    img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+                img = cv2.resize(img, (IMAGE_SIZE, IMAGE_SIZE))
+            else:
+                raise ValueError("Input should be an image file path or a numpy array")
+            
+            img_tensor = torch.FloatTensor(img).unsqueeze(0).unsqueeze(0) / 255.0
+            img_tensor = img_tensor.to(device)
+            output = self(img_tensor).item()
+            
+            # 將輸出四捨五入到最接近的整數
+            num_instructions = round(output)
+            
+            # 生成相應數量的繪圖指令
+            instructions = []
+            for _ in range(num_instructions):
+                shape = random.choice(['line', 'rectangle', 'circle', 'ellipse', 'polygon'])
+                if shape == 'line':
+                    instructions.append(f"cv2.line(image, {(random.randint(0, IMAGE_SIZE), random.randint(0, IMAGE_SIZE))}, {(random.randint(0, IMAGE_SIZE), random.randint(0, IMAGE_SIZE))}, {random.randint(0, 255)}, {random.randint(1, 3)})")
+                elif shape == 'rectangle':
+                    instructions.append(f"cv2.rectangle(image, {(random.randint(0, IMAGE_SIZE-10), random.randint(0, IMAGE_SIZE-10))}, {(random.randint(10, IMAGE_SIZE), random.randint(10, IMAGE_SIZE))}, {random.randint(0, 255)}, {random.randint(1, 3)})")
+                elif shape == 'circle':
+                    instructions.append(f"cv2.circle(image, {(random.randint(10, IMAGE_SIZE-10), random.randint(10, IMAGE_SIZE-10))}, {random.randint(5, 30)}, {random.randint(0, 255)}, {random.randint(1, 3)})")
+                elif shape == 'ellipse':
+                    instructions.append(f"cv2.ellipse(image, {(random.randint(10, IMAGE_SIZE-10), random.randint(10, IMAGE_SIZE-10))}, {(random.randint(5, 30), random.randint(5, 30))}, {random.randint(0, 360)}, 0, 360, {random.randint(0, 255)}, {random.randint(1, 3)})")
+                elif shape == 'polygon':
+                    num_points = random.randint(3, 6)
+                    points = [(random.randint(0, IMAGE_SIZE), random.randint(0, IMAGE_SIZE)) for _ in range(num_points)]
+                    instructions.append(f"cv2.polylines(image, [np.array({points})], True, {random.randint(0, 255)}, {random.randint(1, 3)})")
+              
+            
+            return instructions
+
+def train(model, train_loader, optimizer, criterion):
+    model.train()
+    total_loss = 0
+    for batch_idx, (data, target) in enumerate(train_loader):
+        data, target = data.to(device), target.float().to(device)
+        optimizer.zero_grad()
+        output = model(data).squeeze()
+        loss = criterion(output, target)
+        loss.backward()
+        optimizer.step()
+        total_loss += loss.item()
+        if batch_idx % 100 == 0:
+            print(f'Train Batch {batch_idx}/{len(train_loader)} Loss: {loss.item():.6f}')
+    return total_loss / len(train_loader)
+
+def test(model, test_loader, criterion, print_predictions=False):
+    model.eval()
+    test_loss = 0
+    all_predictions = []
+    all_targets = []
+    with torch.no_grad():
+        for data, target in test_loader:
+            data, target = data.to(device), target.float().to(device)
+            output = model(data).squeeze()
+            test_loss += criterion(output, target).item()
+            all_predictions.extend(output.cpu().numpy())
+            all_targets.extend(target.cpu().numpy())
+    
+    test_loss /= len(test_loader)
+    print(f'Test set: Average loss: {test_loss:.4f}')
+    
+    if print_predictions:
+        print("Sample predictions:")
+        for pred, targ in zip(all_predictions[:10], all_targets[:10]):
+            print(f"Prediction: {pred:.2f}, Target: {targ:.2f}")
+    
+    return test_loss, all_predictions, all_targets
+
+def train1(NUM_SAMPLES=NUM_SAMPLES, maxNumShape=1, EPOCHS=EPOCHS):
+    model = SimpleModel(path=os.path.join(Gbase, 'best_model.pth')).to(device)
+    optimizer = optim.Adam(model.parameters(), lr=LEARNING_RATE)
+    
+    optimizer_path = os.path.join(Gbase, 'optimizer.pth')
+    if os.path.exists(optimizer_path):
+        print("Loading optimizer state...")
+        optimizer.load_state_dict(torch.load(optimizer_path, map_location=device))
+    
+    criterion = nn.MSELoss()
+    
+    seed = 618 * 382 * 33
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed(seed)
+
+    dataset = generate_dataset(NUM_SAMPLES=NUM_SAMPLES, maxNumShape=maxNumShape)
+    train_size = int(0.8 * len(dataset))
+    train_dataset = ImageDataset(dataset[:train_size])
+    test_dataset = ImageDataset(dataset[train_size:])
+
+    train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True)
+    test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=True)
+
+    best_loss = float('inf')
+
+    for epoch in range(EPOCHS):
+        print(f'Epoch {epoch+1}/{EPOCHS}')
+        train_loss = train(model, train_loader, optimizer, criterion)
+        test_loss, predictions, targets = test(model, test_loader, criterion, print_predictions=True)
+        
+        if test_loss < best_loss:
+            best_loss = test_loss
+            torch.save(model.state_dict(), os.path.join(Gbase, 'best_model.pth'))
+            torch.save(optimizer.state_dict(), os.path.join(Gbase, 'optimizer.pth'))
+            print(f"New best model saved with test loss: {best_loss:.4f}")
+
+
+
+
+def main():
+    # Set random seed
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = SimpleModel(path=Gbase+ 'best_model.pth').to(device)
+    optimizer = optim.Adam(model.parameters(), lr=LEARNING_RATE)
+    if os.path.exists(Gbase+'optimizer.pth'):
+        print("Loading optimizer state...")
+        optimizer.load_state_dict(torch.load('optimizer.pth'))
+    criterion = nn.MSELoss()
+    test_image =Gbase+"image.jpg"
+    # np.random.randint(0, 256, (IMAGE_SIZE, IMAGE_SIZE), dtype=np.uint8)
+    instructions = model.predict(test_image)
+    print("Generated instructions:")
+    for instruction in instructions:
+        print(instruction)
+    # 檢查是否存在已保存的優化器狀態
+   
+    #return 
+    seed = 618 * 382 * 33
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+
+    # Generate dataset
+    dataset = generate_dataset()
+
+    # Split dataset into train and test
+    train_size = int(0.8 * len(dataset))
+    train_dataset = ImageDataset(dataset[:train_size])
+    test_dataset = ImageDataset(dataset[train_size:])
+
+    train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True)
+    test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=True)
+
+    
+
+    best_loss = float('inf')
+
+    for epoch in range(EPOCHS):
+        print(f'Epoch {epoch+1}/{EPOCHS}')
+        train_loss = train(model, train_loader, optimizer, criterion, device)
+        test_loss, predictions, targets = test(model, test_loader, criterion, device, print_predictions=True)
+        
+        if test_loss < best_loss:
+            best_loss = test_loss
+            torch.save(model.state_dict(),Gbase+ 'best_model.pth')
+            torch.save(optimizer.state_dict(),Gbase+ 'optimizer.pth')
+            print(f"New best model saved with test loss: {best_loss:.4f}")
+
+    # 測試 predict 方法
+    
+
+if __name__ == "__main__":
+    train1(NUM_SAMPLES=1000 ,maxNumShape=1, EPOCHS=100)
+    train1(NUM_SAMPLES=1000 ,maxNumShape=1, EPOCHS=100)
+    train1(NUM_SAMPLES=1000 ,maxNumShape=1, EPOCHS=100)
+    train1(NUM_SAMPLES=10000 ,maxNumShape=2, EPOCHS=10)
+    train1(NUM_SAMPLES=10000 ,maxNumShape=3,  EPOCHS=10)
+    train1(NUM_SAMPLES=100000 ,maxNumShape=5, EPOCHS=10)
+    train1(NUM_SAMPLES=100000 ,maxNumShape=5, EPOCHS=10)
+    train1(NUM_SAMPLES=100000 ,maxNumShape=5, EPOCHS=10)
+    while True:
+        train1(NUM_SAMPLES=100000 ,maxNumShape=8, EPOCHS=10)
+    
+    

myImage.py

@@ -0,0 +1,34 @@
+from PIL import Image
+import os,cv2
+import numpy as np
+def listImages(d):
+    images = []
+    for f in os.scandir(d):
+        if f.is_file() and f.name.split(".")[-1].lower() in (
+            "jpg",
+            "jpeg",  # 添加 "jpeg" 格式
+            "png",
+            "bmp",
+            "svg",
+            "webp",
+        ):
+            images.append(f.path)
+    return images
+
+def ImageToCV(img):
+    return cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)
+
+def ImageFromBytes (content):
+    return Image.open(BytesIO(content))  
+
+def ImageToBytes (img,format="JPEG"):
+    return img.save(BytesIO(), format=format).getvalue()
+
+def CVtoImage(img):
+    return Image.fromarray(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))
+
+def CVfromBytes(img_bytes):
+    return cv2.imdecode(np.frombuffer(img_bytes, dtype=np.uint8)  , 1) 
+
+def CVtoBytes (img,format=".jpg"):
+    return cv2.imencode(format,img)[1].tobytes()