Upload 4 files

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+from PIL import Image
+import torch
+import torchvision.transforms as transforms
+from model import RetinaNet  # Import your RetinaNet model definition
+
+# Define the image transformation pipeline
+image_transform = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+])
+
+# Load the model
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+model = RetinaNet(num_classes=2).to(device)
+model.load_state_dict(torch.load("retinanet_best_model.pth", map_location=device))
+model.eval()
+
+# Prediction function
+def predict_image(image):
+    # Preprocess the image
+    img = Image.fromarray(image).convert('RGB')  # Convert Gradio input to PIL Image
+    input_tensor = image_transform(img).unsqueeze(0).to(device)
+
+    # Perform inference
+    with torch.no_grad():
+        prediction = model(input_tensor.float())
+        sum_value = abs(torch.sum(prediction[0]))
+        p_true = abs(prediction[0][0])
+        p_false = abs(prediction[0][1])
+
+    # Interpret the prediction
+    if p_true > 0.7:
+        result = "Accepted"
+        confidence = float(p_true)
+    else:
+        result = "Rejected"
+        confidence = float(p_false)
+
+    return f"Result: {result}, Confidence: {confidence:.2f}"
+
+# Create the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# RetinaNet Model Prediction")
+    with gr.Row():
+        image_input = gr.Image(label="Upload Image", type="numpy")
+        output_text = gr.Textbox(label="Prediction Result")
+    predict_button = gr.Button("Predict")
+    predict_button.click(predict_image, inputs=image_input, outputs=output_text)
+
+# Launch the app
+demo.launch()

model.py

@@ -0,0 +1,47 @@
+import numpy as np
+import torch
+import torchvision.transforms as transforms
+import torch.nn as nn
+from torch.utils.data import DataLoader, Dataset
+from torchvision import transforms, datasets, models
+
+# Define model
+class RetinaNet(nn.Module):
+    def __init__(self, num_classes=2):
+        super(RetinaNet, self).__init__()
+        self.backbone = models.resnet50(weights=models.ResNet50_Weights.IMAGENET1K_V1)
+
+        # Freeze backbone parameters
+        for param in self.backbone.parameters():
+            param.requires_grad = False
+
+        # Unfreeze later layers
+        for param in self.backbone.layer3.parameters():
+            param.requires_grad = True
+        for param in self.backbone.layer4.parameters():
+            param.requires_grad = False
+
+        # Modified classifier head
+        self.classifier = nn.Sequential(
+            nn.Linear(2048, 512),
+            nn.ReLU(),
+            nn.Dropout(0.5),
+            nn.Linear(512, num_classes)
+            # nn.Sigmoid()
+        )
+
+    def forward(self, x):
+        x = self.backbone.conv1(x)
+        x = self.backbone.bn1(x)
+        x = self.backbone.relu(x)
+        x = self.backbone.maxpool(x)
+
+        x = self.backbone.layer1(x)
+        x = self.backbone.layer2(x)
+        x = self.backbone.layer3(x)
+        x = self.backbone.layer4(x)
+
+        x = self.backbone.avgpool(x)
+        x = torch.flatten(x, 1)
+        x = self.classifier(x)
+        return x    

requirements.txt

@@ -0,0 +1,107 @@
+absl-py==2.1.0
+aiohappyeyeballs==2.4.6
+aiohttp==3.11.12
+aiosignal==1.3.2
+astunparse==1.6.3
+attrs==25.1.0
+blinker==1.9.0
+CacheControl==0.14.2
+cachetools==5.5.1
+certifi==2025.1.31
+cffi==1.17.1
+charset-normalizer==2.1.1
+click==8.1.8
+colorama==0.4.6
+cryptography==44.0.1
+datasets==3.2.0
+dill==0.3.8
+filelock==3.17.0
+firebase-admin==6.6.0
+Flask==3.1.0
+Flask-Cors==5.0.0
+flatbuffers==25.1.24
+frozenlist==1.5.0
+fsspec==2024.9.0
+gast==0.6.0
+google-api-core==2.24.1
+google-api-python-client==2.161.0
+google-auth==2.38.0
+google-auth-httplib2==0.2.0
+google-cloud-core==2.4.1
+google-cloud-firestore==2.20.0
+google-cloud-storage==3.0.0
+google-crc32c==1.6.0
+google-pasta==0.2.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.67.0
+greenlet==3.1.1
+grpcio==1.70.0
+gradio==3.41.2
+grpcio-status==1.70.0
+h5py==3.12.1
+httplib2==0.22.0
+idna==3.10
+itsdangerous==2.2.0
+Jinja2==3.1.5
+keras==3.8.0
+libclang==18.1.1
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+mdurl==0.1.2
+ml-dtypes==0.4.1
+mpmath==1.3.0
+msgpack==1.1.0
+multidict==6.1.0
+multiprocess==0.70.16
+namex==0.0.8
+networkx==3.4.2
+numpy==2.0.2
+opencv-python==4.11.0.86
+opt_einsum==3.4.0
+optree==0.14.0
+packaging==24.2
+pandas==2.2.3
+pillow==11.1.0
+propcache==0.2.1
+proto-plus==1.26.0
+protobuf==5.29.3
+psycopg2-binary==2.9.10
+pyarrow==19.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+Pygments==2.19.1
+PyJWT==2.10.1
+pyparsing==3.2.1
+python-dateutil==2.9.0.post0
+pytz==2025.1
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+rsa==4.9
+safetensors==0.5.2
+setuptools==75.8.0
+six==1.17.0
+SQLAlchemy==2.0.38
+sympy==1.13.1
+tensorboard==2.18.0
+tensorboard-data-server==0.7.2
+tensorflow==2.18.0
+tensorflow_intel==2.18.0
+termcolor==2.5.0
+tokenizers==0.21.0
+torch==2.6.0
+torchvision==0.21.0
+tqdm==4.67.1
+transformers==4.48.3
+typing_extensions==4.12.2
+tzdata==2025.1
+uritemplate==4.1.1
+urllib3==1.26.20
+Werkzeug==3.1.3
+wheel==0.45.1
+wrapt==1.17.2
+xxhash==3.5.0
+yarl==1.18.3

retinanet_best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf5190eab09966edb71eb3cf8c67d358d37badb96ce21bd611901bdf5b8d0cc
+size 106756882