Create app.py

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+from transformers import AutoImageProcessor, ResNetForImageClassification, YolosFeatureExtractor, YolosForObjectDetection
+import torch
+
+
+
+
+def detect(image1, image2):
+    ### Image 1, the object ### 
+    processor = AutoImageProcessor.from_pretrained("microsoft/resnet-50")
+    model = ResNetForImageClassification.from_pretrained("microsoft/resnet-50")
+    
+    inputs = processor(image, return_tensors="pt")
+    
+    with torch.no_grad():
+        logits = model(**inputs).logits
+    
+    # model predicts one of the 1000 ImageNet classes
+    predicted_label = logits.argmax(-1).item()
+    print(model.config.id2label[predicted_label])
+    
+    
+    
+    ### Image 2, object detections ###
+    from PIL import Image
+    import requests
+    
+    feature_extractor = YolosFeatureExtractor.from_pretrained('hustvl/yolos-small')
+    model = YolosForObjectDetection.from_pretrained('hustvl/yolos-small')
+    
+    inputs = feature_extractor(images=image, return_tensors="pt")
+    outputs = model(**inputs)
+    
+    # model predicts bounding boxes and corresponding COCO classes
+    logits = outputs.logits
+    bboxes = outputs.pred_boxes
+
+    return model.config.id2label[predicted_label], bboxes
+
+
+
+
+demo = gr.Interface(
+    fn=detect,
+    inputs=[gr.inputs.Image(label="Object to detect"), gr.inputs.Image(label="Image to detect object in")],
+    outputs=["prediction", "bounding boxes"],
+    title="Object Counts in Image"
+)
+
+demo.launch()