adding yoloxl

app.py

@@ -6,6 +6,7 @@ import torch
 import pathlib
 from PIL import Image
 from transformers import AutoFeatureExtractor, DetrForObjectDetection, YolosForObjectDetection
+from keras_cv_attention_models.yolox import *
 
 import os
 
@@ -19,12 +20,16 @@ COLORS = [
     [0.301, 0.745, 0.933]
 ]
 
-def make_prediction(img, feature_extractor, model):
+def make_prediction(img, feature_extractor, model, model_name):
     inputs = feature_extractor(img, return_tensors="pt")
     outputs = model(**inputs)
-    img_size = torch.tensor([tuple(reversed(img.size))])
-    processed_outputs = feature_extractor.post_process(outputs, img_size)
-    return processed_outputs[0]
+    if 'yolox' in model_name:
+        processed_outputs = {}
+        processed_outputs['boxes'], processed_outputs['labels'], processed_outputs['scores'] = model.decode_predictions(outputs)[0]
+    else:
+        img_size = torch.tensor([tuple(reversed(img.size))])
+        processed_outputs = feature_extractor.post_process(outputs, img_size)[0]
+    return processed_outputs
 
 def fig2img(fig):
     buf = io.BytesIO()
@@ -53,26 +58,23 @@ def visualize_prediction(pil_img, output_dict, threshold=0.7, id2label=None):
     return fig2img(plt.gcf())
 
 def detect_objects(model_name,url_input,image_input,threshold):
-    
-    #Extract model and feature extractor
-    feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
-    
     if 'detr' in model_name:
-        
-        model = DetrForObjectDetection.from_pretrained(model_name)
-        
+        model = DetrForObjectDetection.from_pretrained(model_name
+		feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
     elif 'yolos' in model_name:
-    
         model = YolosForObjectDetection.from_pretrained(model_name)
+		feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+    elif 'yolox' in model_name:
+        model = YOLOXL(pretrained="coco")
+		feature_extractor = model.preprocess_input
     
     if validators.url(url_input):
-        image = Image.open(requests.get(url_input, stream=True).raw)
-        
+        image = Image.open(requests.get(url_input, stream=True).raw)     
     elif image_input:
         image = image_input
     
     #Make prediction
-    processed_outputs = make_prediction(image, feature_extractor, model)
+    processed_outputs = make_prediction(image, feature_extractor, model, model_name)
     
     #Visualize prediction
     viz_img = visualize_prediction(image, processed_outputs, threshold, model.config.id2label)
@@ -98,7 +100,7 @@ Links to HuggingFace Models:
 
 """
 
-models = ["facebook/detr-resnet-50","facebook/detr-resnet-101",'hustvl/yolos-small','hustvl/yolos-tiny']
+models = ["facebook/detr-resnet-50","facebook/detr-resnet-101","hustvl/yolos-small","hustvl/yolos-tiny","yoloxl"]
 urls = ["https://c8.alamy.com/comp/J2AB4K/the-new-york-stock-exchange-on-the-wall-street-in-new-york-J2AB4K.jpg"]
 
 css = '''

app_bk.py

@@ -0,0 +1,144 @@
+import io
+import gradio as gr
+import matplotlib.pyplot as plt
+import requests, validators
+import torch
+import pathlib
+from PIL import Image
+from transformers import AutoFeatureExtractor, DetrForObjectDetection, YolosForObjectDetection
+
+import os
+
+# colors for visualization
+COLORS = [
+    [0.000, 0.447, 0.741],
+    [0.850, 0.325, 0.098],
+    [0.929, 0.694, 0.125],
+    [0.494, 0.184, 0.556],
+    [0.466, 0.674, 0.188],
+    [0.301, 0.745, 0.933]
+]
+
+def make_prediction(img, feature_extractor, model):
+    inputs = feature_extractor(img, return_tensors="pt")
+    outputs = model(**inputs)
+    img_size = torch.tensor([tuple(reversed(img.size))])
+    processed_outputs = feature_extractor.post_process(outputs, img_size)
+    return processed_outputs[0]
+
+def fig2img(fig):
+    buf = io.BytesIO()
+    fig.savefig(buf)
+    buf.seek(0)
+    img = Image.open(buf)
+    return img
+
+
+def visualize_prediction(pil_img, output_dict, threshold=0.7, id2label=None):
+    keep = output_dict["scores"] > threshold
+    boxes = output_dict["boxes"][keep].tolist()
+    scores = output_dict["scores"][keep].tolist()
+    labels = output_dict["labels"][keep].tolist()
+    if id2label is not None:
+        labels = [id2label[x] for x in labels]
+
+    plt.figure(figsize=(16, 10))
+    plt.imshow(pil_img)
+    ax = plt.gca()
+    colors = COLORS * 100
+    for score, (xmin, ymin, xmax, ymax), label, color in zip(scores, boxes, labels, colors):
+        ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=color, linewidth=3))
+        ax.text(xmin, ymin, f"{label}: {score:0.2f}", fontsize=15, bbox=dict(facecolor="yellow", alpha=0.5))
+    plt.axis("off")
+    return fig2img(plt.gcf())
+
+def detect_objects(model_name,url_input,image_input,threshold):
+    
+    #Extract model and feature extractor
+    feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
+    
+    if 'detr' in model_name:
+        
+        model = DetrForObjectDetection.from_pretrained(model_name)
+        
+    elif 'yolos' in model_name:
+    
+        model = YolosForObjectDetection.from_pretrained(model_name)
+    
+    if validators.url(url_input):
+        image = Image.open(requests.get(url_input, stream=True).raw)
+        
+    elif image_input:
+        image = image_input
+    
+    #Make prediction
+    processed_outputs = make_prediction(image, feature_extractor, model)
+    
+    #Visualize prediction
+    viz_img = visualize_prediction(image, processed_outputs, threshold, model.config.id2label)
+    
+    return viz_img   
+        
+def set_example_image(example: list) -> dict:
+    return gr.Image.update(value=example[0])
+
+def set_example_url(example: list) -> dict:
+    return gr.Textbox.update(value=example[0])
+
+
+title = """<h1 id="title">Object Detection App with DETR and YOLOS</h1>"""
+
+description = """
+Links to HuggingFace Models:
+- [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50)  
+- [facebook/detr-resnet-101](https://huggingface.co/facebook/detr-resnet-101)  
+- [hustvl/yolos-small](https://huggingface.co/hustvl/yolos-small)
+- [hustvl/yolos-tiny](https://huggingface.co/hustvl/yolos-tiny)
+"""
+
+models = ["facebook/detr-resnet-50","facebook/detr-resnet-101",'hustvl/yolos-small','hustvl/yolos-tiny']
+urls = ["https://c8.alamy.com/comp/J2AB4K/the-new-york-stock-exchange-on-the-wall-street-in-new-york-J2AB4K.jpg"]
+
+css = '''
+h1#title {
+  text-align: center;
+}
+'''
+demo = gr.Blocks(css=css)
+
+with demo:
+    gr.Markdown(title)
+    gr.Markdown(description)
+    options = gr.Dropdown(choices=models,label='Select Object Detection Model',show_label=True)
+    slider_input = gr.Slider(minimum=0.2,maximum=1,value=0.5,label='Prediction Threshold')
+    
+    with gr.Tabs():
+        with gr.TabItem('Image URL'):
+            with gr.Row():
+                url_input = gr.Textbox(lines=2,label='Enter valid image URL here..')
+                img_output_from_url = gr.Image(shape=(650,650))
+                
+            with gr.Row():
+                example_url = gr.Dataset(components=[url_input],samples=[[str(url)] for url in urls])
+            
+            url_but = gr.Button('Detect')
+     
+        with gr.TabItem('Image Upload'):
+            with gr.Row():
+                img_input = gr.Image(type='pil')
+                img_output_from_upload= gr.Image(shape=(650,650))
+                
+            with gr.Row(): 
+                example_images = gr.Dataset(components=[img_input],
+                                            samples=[[path.as_posix()]
+                                                     for path in sorted(pathlib.Path('images').rglob('*.JPG'))])
+                
+            img_but = gr.Button('Detect')
+        
+    
+    url_but.click(detect_objects,inputs=[options,url_input,img_input,slider_input],outputs=img_output_from_url,queue=True)
+    img_but.click(detect_objects,inputs=[options,url_input,img_input,slider_input],outputs=img_output_from_upload,queue=True)
+    example_images.click(fn=set_example_image,inputs=[example_images],outputs=[img_input])
+    example_url.click(fn=set_example_url,inputs=[example_url],outputs=[url_input])
+    
+demo.launch(enable_queue=True)

requirements.txt

@@ -5,3 +5,4 @@ torch==1.10.1
 validators==0.18.2
 timm==0.5.4
 transformers
+keras_cv_attention_models==1.2.9