Add gradio app HF

.gitattributes copy

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+from utils.model import load_model
+from utils.transformations import transform_image
+from utils.prediction import predict_class
+
+# Load the model only once when the application starts
+net = load_model()
+
+def classify_image(image_path):
+    """
+    Main function for the Gradio interface.
+    """
+    image_tensor = transform_image(image_path)
+    predicted_class, confidence = predict_class(image_tensor, net)
+    return f"Predicted Class: {predicted_class}, Confidence: {confidence:.2f}"
+
+iface = gr.Interface(
+    fn=classify_image,
+    inputs=gr.Image(type="filepath"),
+    outputs="text",
+    title="Galaxy Classification",
+    description="Upload an image of a galaxy to classify it."
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,155 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+_libgcc_mutex=0.1=conda_forge
+_openmp_mutex=4.5=2_gnu
+aiofiles=23.2.1=pypi_0
+altair=5.3.0=pypi_0
+annotated-types=0.7.0=pypi_0
+anyio=4.4.0=pypi_0
+asttokens=2.4.1=pyhd8ed1ab_0
+attrs=23.2.0=pypi_0
+bzip2=1.0.8=h4bc722e_7
+ca-certificates=2024.7.4=hbcca054_0
+certifi=2024.7.4=pypi_0
+charset-normalizer=3.3.2=pypi_0
+click=8.1.7=pypi_0
+comm=0.2.2=pyhd8ed1ab_0
+contourpy=1.2.1=pypi_0
+cycler=0.12.1=pypi_0
+debugpy=1.8.2=py312h7070661_0
+decorator=5.1.1=pyhd8ed1ab_0
+dnspython=2.6.1=pypi_0
+efficientnet-pytorch=0.7.1=pypi_0
+email-validator=2.2.0=pypi_0
+exceptiongroup=1.2.2=pyhd8ed1ab_0
+executing=2.0.1=pyhd8ed1ab_0
+fastapi=0.111.1=pypi_0
+fastapi-cli=0.0.4=pypi_0
+ffmpy=0.3.2=pypi_0
+filelock=3.15.4=pypi_0
+fonttools=4.53.1=pypi_0
+fsspec=2024.6.1=pypi_0
+gradio=4.38.1=pypi_0
+gradio-client=1.1.0=pypi_0
+h11=0.14.0=pypi_0
+httpcore=1.0.5=pypi_0
+httptools=0.6.1=pypi_0
+httpx=0.27.0=pypi_0
+huggingface-hub=0.24.0=pypi_0
+idna=3.7=pypi_0
+importlib-metadata=8.0.0=pyha770c72_0
+importlib-resources=6.4.0=pypi_0
+importlib_metadata=8.0.0=hd8ed1ab_0
+ipykernel=6.29.5=pyh3099207_0
+ipython=8.26.0=pyh707e725_0
+jedi=0.19.1=pyhd8ed1ab_0
+jinja2=3.1.4=pypi_0
+joblib=1.4.2=pypi_0
+jsonschema=4.23.0=pypi_0
+jsonschema-specifications=2023.12.1=pypi_0
+jupyter_client=8.6.2=pyhd8ed1ab_0
+jupyter_core=5.7.2=py312h7900ff3_0
+keyutils=1.6.1=h166bdaf_0
+kiwisolver=1.4.5=pypi_0
+krb5=1.21.3=h659f571_0
+ld_impl_linux-64=2.40=hf3520f5_7
+libedit=3.1.20191231=he28a2e2_2
+libexpat=2.6.2=h59595ed_0
+libffi=3.4.2=h7f98852_5
+libgcc-ng=14.1.0=h77fa898_0
+libgomp=14.1.0=h77fa898_0
+libnsl=2.0.1=hd590300_0
+libsodium=1.0.18=h36c2ea0_1
+libsqlite=3.46.0=hde9e2c9_0
+libstdcxx-ng=14.1.0=hc0a3c3a_0
+libuuid=2.38.1=h0b41bf4_0
+libxcrypt=4.4.36=hd590300_1
+libzlib=1.3.1=h4ab18f5_1
+markdown-it-py=3.0.0=pypi_0
+markupsafe=2.1.5=pypi_0
+matplotlib=3.9.1=pypi_0
+matplotlib-inline=0.1.7=pyhd8ed1ab_0
+mdurl=0.1.2=pypi_0
+mpmath=1.3.0=pypi_0
+ncurses=6.5=h59595ed_0
+nest-asyncio=1.6.0=pyhd8ed1ab_0
+networkx=3.3=pypi_0
+numpy=2.0.0=pypi_0
+nvidia-cublas-cu12=12.1.3.1=pypi_0
+nvidia-cuda-cupti-cu12=12.1.105=pypi_0
+nvidia-cuda-nvrtc-cu12=12.1.105=pypi_0
+nvidia-cuda-runtime-cu12=12.1.105=pypi_0
+nvidia-cudnn-cu12=8.9.2.26=pypi_0
+nvidia-cufft-cu12=11.0.2.54=pypi_0
+nvidia-curand-cu12=10.3.2.106=pypi_0
+nvidia-cusolver-cu12=11.4.5.107=pypi_0
+nvidia-cusparse-cu12=12.1.0.106=pypi_0
+nvidia-nccl-cu12=2.20.5=pypi_0
+nvidia-nvjitlink-cu12=12.5.82=pypi_0
+nvidia-nvtx-cu12=12.1.105=pypi_0
+openssl=3.3.1=h4bc722e_2
+orjson=3.10.6=pypi_0
+packaging=24.1=pyhd8ed1ab_0
+pandas=2.2.2=pypi_0
+parso=0.8.4=pyhd8ed1ab_0
+pexpect=4.9.0=pyhd8ed1ab_0
+pickleshare=0.7.5=py_1003
+pillow=10.4.0=pypi_0
+pip=24.0=pyhd8ed1ab_0
+platformdirs=4.2.2=pyhd8ed1ab_0
+prompt-toolkit=3.0.47=pyha770c72_0
+psutil=6.0.0=py312h9a8786e_0
+ptyprocess=0.7.0=pyhd3deb0d_0
+pure_eval=0.2.2=pyhd8ed1ab_0
+pydantic=2.8.2=pypi_0
+pydantic-core=2.20.1=pypi_0
+pydub=0.25.1=pypi_0
+pygments=2.18.0=pyhd8ed1ab_0
+pyparsing=3.1.2=pypi_0
+python=3.12.4=h194c7f8_0_cpython
+python-dateutil=2.9.0=pyhd8ed1ab_0
+python-dotenv=1.0.1=pypi_0
+python-multipart=0.0.9=pypi_0
+python_abi=3.12=4_cp312
+pytz=2024.1=pypi_0
+pyyaml=6.0.1=pypi_0
+pyzmq=26.0.3=py312h8fd38d8_0
+readline=8.2=h8228510_1
+referencing=0.35.1=pypi_0
+requests=2.32.3=pypi_0
+rich=13.7.1=pypi_0
+rpds-py=0.19.0=pypi_0
+ruff=0.5.3=pypi_0
+scikit-learn=1.5.1=pypi_0
+scipy=1.14.0=pypi_0
+semantic-version=2.10.0=pypi_0
+setuptools=71.0.3=pyhd8ed1ab_0
+shellingham=1.5.4=pypi_0
+six=1.16.0=pyh6c4a22f_0
+sniffio=1.3.1=pypi_0
+stack_data=0.6.2=pyhd8ed1ab_0
+starlette=0.37.2=pypi_0
+sympy=1.13.1=pypi_0
+threadpoolctl=3.5.0=pypi_0
+tk=8.6.13=noxft_h4845f30_101
+tomlkit=0.12.0=pypi_0
+toolz=0.12.1=pypi_0
+torch=2.3.1=pypi_0
+torchvision=0.18.1=pypi_0
+tornado=6.4.1=py312h9a8786e_0
+tqdm=4.66.4=pypi_0
+traitlets=5.14.3=pyhd8ed1ab_0
+typer=0.12.3=pypi_0
+typing_extensions=4.12.2=pyha770c72_0
+tzdata=2024.1=pypi_0
+urllib3=2.2.2=pypi_0
+uvicorn=0.30.1=pypi_0
+uvloop=0.19.0=pypi_0
+watchfiles=0.22.0=pypi_0
+wcwidth=0.2.13=pyhd8ed1ab_0
+websockets=11.0.3=pypi_0
+wheel=0.43.0=pyhd8ed1ab_1
+xz=5.2.6=h166bdaf_0
+zeromq=4.3.5=h75354e8_4
+zipp=3.19.2=pyhd8ed1ab_0

utils/model.py

@@ -0,0 +1,25 @@
+import os
+import torch
+import torch.nn as nn
+from efficientnet_pytorch import EfficientNet
+
+class EffNet(nn.Module):
+    def __init__(self, n_classes):
+        super(EffNet, self).__init__()
+        self.b4 = EfficientNet.from_pretrained('efficientnet-b0')
+        self.drop = nn.Dropout(0.2)
+        self.fc = nn.Linear(1000, n_classes)
+
+    def forward(self, image):
+        x = self.b4(image)
+        x = self.drop(x)
+        out = self.fc(x)
+        return out
+
+def load_model():
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    net = EffNet(n_classes=2).to(device)
+    model_path = os.path.join(os.path.dirname(__file__), 'models', 'modelo_galaxias.pth')
+    net.load_state_dict(torch.load(model_path))  # Adjust path if needed
+    net.eval()
+    return net

utils/models/modelo_galaxias.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36aef445889deb63f7581a82cda3b0410a8bad183ff8a8dfd211460e8d79f4c4
+size 21459918

utils/prediction.py

@@ -0,0 +1,26 @@
+import torch
+
+def predict_class(image_tensor, model):
+    """
+    Predicts the class of the image using the model.
+
+    Args:
+        image_tensor (torch.Tensor): Transformed image.
+        model (torch.nn.Module): The loaded PyTorch model.
+
+    Returns:
+        str: Predicted class (eliptical or spiral).
+        float: Confidence of the prediction.
+    """
+
+    with torch.no_grad():
+        device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+        output = model(image_tensor.to(device))
+        probabilities = torch.softmax(output, dim=1)
+        predicted_class_index = torch.argmax(probabilities, dim=1).item()
+        confidence = torch.max(probabilities).item()
+
+    classes = ['eliptical', 'spiral']
+    predicted_class = classes[predicted_class_index]
+
+    return predicted_class, confidence

utils/transformations.py

@@ -0,0 +1,27 @@
+from PIL import Image
+import torchvision.transforms as transforms
+
+IMAGE_SHAPE = (200, 200)
+
+def transform_image(image_path):
+    """
+    Loads, transforms, and prepares the image for the model.
+
+    Args:
+        image_path (str): Path to the image.
+
+    Returns:
+        torch.Tensor: Transformed image ready for the model.
+    """
+
+    transform = transforms.Compose([
+        transforms.Resize(IMAGE_SHAPE),
+        transforms.RandomHorizontalFlip(),
+        transforms.RandomRotation(degrees=10),
+        transforms.ToTensor(),
+    ])
+
+    image = Image.open(image_path).convert('RGB')
+    image = transform(image)
+    image = image.unsqueeze(0)  # Add batch dimension
+    return image