Upload do modulo captcha TJMG

tjmg.py

@@ -0,0 +1,108 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torchvision import transforms
+from PIL import Image
+from safetensors.torch import load_file
+from huggingface_hub import hf_hub_download
+
+# Definição da arquitetura da rede neural
+class CaptchaCNN(nn.Module):
+    def __init__(self, input_dim, output_ndigits, output_vocab_size, dropout=(0.25, 0.5), dense_units=200, vocab=None):
+        super().__init__()
+        self.input_dim = input_dim
+        self.output_ndigits = output_ndigits
+        self.output_vocab_size = output_vocab_size
+        self.vocab = vocab
+
+        self.batchnorm0 = nn.BatchNorm2d(3)
+        self.conv1 = nn.Conv2d(3, 32, kernel_size=3)
+        self.batchnorm1 = nn.BatchNorm2d(32)
+        self.conv2 = nn.Conv2d(32, 64, kernel_size=3)
+        self.batchnorm2 = nn.BatchNorm2d(64)
+        self.conv3 = nn.Conv2d(64, 64, kernel_size=3)
+        self.batchnorm3 = nn.BatchNorm2d(64)
+        self.dropout1 = nn.Dropout(dropout[0])
+        self.dropout2 = nn.Dropout(dropout[1])
+
+        # Cálculo das dimensões após as camadas convolucionais
+        def calc_dim(x):
+            for _ in range(3):
+                x = (x - 2) // 2
+            return x
+
+        conv_h = calc_dim(input_dim[0])
+        conv_w = calc_dim(input_dim[1])
+        fc1_in_features = conv_h * conv_w * 64
+
+        self.fc1 = nn.Linear(fc1_in_features, dense_units)
+        self.batchnorm_dense = nn.BatchNorm1d(dense_units)
+        self.fc2 = nn.Linear(dense_units, output_vocab_size * output_ndigits)
+
+    def forward(self, x):
+        x = self.batchnorm0(x)
+        x = F.relu(self.batchnorm1(F.max_pool2d(self.conv1(x), 2)))
+        x = F.relu(self.batchnorm2(F.max_pool2d(self.conv2(x), 2)))
+        x = F.relu(self.batchnorm3(F.max_pool2d(self.conv3(x), 2)))
+
+        x = torch.flatten(x, start_dim=1)
+        x = self.dropout1(x)
+        x = F.relu(self.batchnorm_dense(self.fc1(x)))
+        x = self.dropout2(x)
+        x = self.fc2(x)
+        x = x.view(-1, self.output_ndigits, self.output_vocab_size)
+        return x
+
+
+# Classe principal para carregar o modelo e fazer previsões
+class TJMG:
+    def __init__(self, repo_id="julio/captcha", filename="captcha_model.safetensors"):
+        # Hiperparâmetros do modelo
+        self.input_dim = (40, 110)
+        self.output_vocab_size = 10
+        self.vocab = [str(x) for x in range(10)]
+        self.output_ndigits = 5
+        self.dropout = (0.25, 0.5)
+        self.dense_units = 200
+
+        # Baixar o modelo do Hugging Face
+        model_path = hf_hub_download(repo_id=repo_id, filename=filename)
+
+        # Inicializar o modelo
+        self.model = CaptchaCNN(
+            input_dim=self.input_dim,
+            output_ndigits=self.output_ndigits,
+            output_vocab_size=self.output_vocab_size,
+            dropout=self.dropout,
+            dense_units=self.dense_units,
+            vocab=self.vocab
+        )
+        
+        # Carregar os pesos do modelo
+        state_dict = load_file(model_path)
+        self.model.load_state_dict(state_dict)
+        self.model.eval()
+
+        # Transformação da imagem
+        self.transform = transforms.Compose([
+            transforms.Resize(self.input_dim),
+            transforms.ToTensor(),
+        ])
+
+    def predict(self, image_path):
+        """
+        Faz a previsão de um CAPTCHA.
+        Args:
+            image_path (str): Caminho da imagem do CAPTCHA.
+        Returns:
+            str: Texto previsto para o CAPTCHA.
+        """
+        image = Image.open(image_path).convert('RGB')
+        image = self.transform(image).unsqueeze(0)
+
+        with torch.no_grad():
+            logits = self.model(image)
+
+        preds = torch.argmax(logits, dim=2).squeeze().tolist()
+        predicted_label = ''.join([self.vocab[i] for i in preds])
+        return predicted_label