initial commit

app.py

@@ -0,0 +1,47 @@
+"""
+Simple Gradio app on http://127.0.0.1:7860
+Hugging Face: https://huggingface.co/spaces/andreasmlanger/cat_dog
+"""
+
+import gradio as gr
+import torch
+from torch import nn
+from torchvision import models, transforms
+import os
+
+
+MODEL_PATH = r'cat_dog_RNN.pth'  # path to trained model, needs to be in same directory
+EXAMPLES = [[os.path.join('examples', f)] for f in os.listdir('examples')]  # example images
+CLASS_NAMES = ['cat', 'dog']
+
+# Load model architecture and saved weights
+model = models.resnet50(weights=models.ResNet50_Weights.DEFAULT)
+for param in model.parameters():
+    param.requires_grad = False  # freeze pre-trained weights, so they don't get changed during training
+model.fc = nn.Sequential(
+    nn.Linear(in_features=model.fc.in_features, out_features=512),
+    nn.ReLU(),
+    nn.Dropout(0.2),
+    nn.Linear(512, len(CLASS_NAMES), bias=True)
+)
+model.load_state_dict(torch.load(MODEL_PATH))
+
+
+def predict(img):
+    transform = transforms.Compose([transforms.Resize(size=(224, 224)), transforms.ToTensor()])
+    transformed_image = transform(img).unsqueeze(0)
+    model.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(model(transformed_image), dim=1)
+    return {CLASS_NAMES[i]: float(pred_probs[0][i]) for i in range(len(CLASS_NAMES))}
+
+
+# Create and launch the Gradio demo
+demo = gr.Interface(fn=predict,
+                    inputs=gr.Image(type='pil', label='Image'),
+                    outputs=[gr.Label(num_top_classes=2, label='Predictions')],
+                    examples=EXAMPLES,
+                    title='Cat vs Dog Image Classifier',
+                    description='A residual neuronal network designed to distinguish between cat and dog images.')
+
+demo.launch(debug=False)

cat_dog_RNN.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2fe3ae139b6b5ad651d6de59f8a8e3b88de786a9fd638bcfc8356b65bb397b
+size 98549674

requirements.txt

@@ -0,0 +1,3 @@
+gradio==4.16.0
+torch==2.1.2
+torchvision==0.16.2