Create app.py

app.py

@@ -0,0 +1,83 @@
+import torch
+import gradio as gr
+from PIL import Image
+from huggingface_hub import hf_hub_download
+import importlib.util
+from torchvision import transforms
+
+# Load model
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Download model code
+class_path = hf_hub_download(repo_id="PerceptCLIP/PerceptCLIP_Emotions", filename="modeling.py")
+spec = importlib.util.spec_from_file_location("modeling", class_path)
+modeling = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(modeling)
+
+# Initialize the model
+from modeling import clip_lora_model
+model = clip_lora_model().to(device)
+
+# Load pretrained weights
+model_path = hf_hub_download(repo_id="PerceptCLIP/PerceptCLIP_Emotions", filename="perceptCLIP_Emotions.pth")
+model.load_state_dict(torch.load(model_path, map_location=device))
+model.eval()
+
+# Emotion label mapping
+idx2label = {
+    0: "amusement",
+    1: "awe",
+    2: "contentment",
+    3: "excitement",
+    4: "anger",
+    5: "disgust",
+    6: "fear",
+    7: "sadness"
+}
+
+# Emoji mapping
+emotion_emoji = {
+    "amusement": "😂",
+    "awe": "😲",
+    "contentment": "😊",
+    "excitement": "😃",
+    "anger": "😠",
+    "disgust": "🤢",
+    "fear": "😱",
+    "sadness": "😞"
+}
+
+# Image preprocessing
+def emo_preprocess(image):
+    transform = transforms.Compose([
+        transforms.Resize(224),
+        transforms.CenterCrop(224),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=(0.4814, 0.4578, 0.4082), std=(0.2686, 0.2613, 0.2758)),
+    ])
+    return transform(image).unsqueeze(0).to(device)
+
+# Inference function
+def predict_emotion(image):
+    image = Image.open(image).convert("RGB")
+    image = emo_preprocess(image)
+
+    with torch.no_grad():
+        outputs = model(image)
+        predicted = outputs.argmax(1).item()
+
+    emotion = idx2label[predicted]
+    emoji = emotion_emoji.get(emotion, "❓")  # Default to "?" if no emoji found
+    return f"{emotion} {emoji}"
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_emotion,
+    inputs=gr.inputs.Image(type="pil", label="Upload an Image"),
+    outputs=gr.outputs.Textbox(label="Emotion + Emoji"),
+    title="PerceptCLIP-Emotions",
+    description="This model predicts the emotion evoked by an image and returns the corresponding emoji along with the emotion name."
+)
+
+if __name__ == "__main__":
+    iface.launch()