add app.py

app.py

@@ -0,0 +1,109 @@
+
+import torch
+
+from transformers import AutoImageProcessor, AutoModelForObjectDetection
+#from transformers import pipeline
+
+from PIL import Image
+import matplotlib.pyplot as plt
+import matplotlib.patches as patches
+
+import io
+from random import choice
+
+
+image_processor_tiny = AutoImageProcessor.from_pretrained("hustvl/yolos-tiny")
+model_tiny = AutoModelForObjectDetection.from_pretrained("hustvl/yolos-tiny")
+
+image_processor_small = AutoImageProcessor.from_pretrained("hustvl/yolos-small")
+model_small = AutoModelForObjectDetection.from_pretrained("hustvl/yolos-small")
+
+
+import gradio as gr
+
+
+COLORS = ["#ff7f7f", "#ff7fbf", "#ff7fff", "#bf7fff",
+            "#7f7fff", "#7fbfff", "#7fffff", "#7fffbf",
+            "#7fff7f", "#bfff7f", "#ffff7f", "#ffbf7f"]
+
+fdic = {
+    "family" : "Impact",
+    "style" : "italic",
+    "size" : 15,
+    "color" : "yellow",
+    "weight" : "bold"
+}
+
+
+def get_figure(in_pil_img, in_results):
+    plt.figure(figsize=(16, 10))
+    plt.imshow(in_pil_img)
+    ax = plt.gca()
+
+    for score, label, box in zip(in_results["scores"], in_results["labels"], in_results["boxes"]):
+        selected_color = choice(COLORS)
+
+        #box = [round(i, 2) for i in box.tolist()]
+        x, y, w, h = int(box[0]), int(box[1]), int(box[2]-box[0]), int(box[3]-box[1])
+        print(x, y, w, h)
+        ax.add_patch(plt.Rectangle((x, y), w, h, fill=False, color=selected_color, linewidth=3))
+        ax.text(x, y, f"{model_tiny.config.id2label[label.item()]}: {round(score.item()*100, 1)}%", fontdict=fdic)
+        #print(
+        #    f"Detected {model_tiny.config.id2label[label.item()]} with confidence "
+        #    f"{round(score.item(), 3)} at location {box}"
+        #)
+
+    plt.axis("off")
+
+    return plt.gcf()
+
+
+def infer(in_model, in_threshold, in_pil_img):
+    print(type(in_pil_img))
+    print(threshold)
+    inputs = image_processor_tiny(images=in_pil_img, return_tensors="pt")
+    outputs = model_tiny(**inputs)
+
+    # convert outputs (bounding boxes and class logits) to COCO API
+    target_sizes = torch.tensor([in_pil_img.size[::-1]])
+    results = image_processor_tiny.post_process_object_detection(outputs, threshold=in_threshold, target_sizes=target_sizes)[
+        0
+    ]
+    print(results)
+
+    figure = get_figure(in_pil_img, results)
+
+    buf = io.BytesIO()
+    figure.savefig(buf, bbox_inches='tight')
+    buf.seek(0)
+    output_pil_img = Image.open(buf)
+
+    return output_pil_img
+
+
+#from transformers.models.flava import modeling_flava
+with gr.Blocks(css=".gradio-container {background:lightyellow;color:red;}", title="テスト"
+               ) as demo:
+    #sample_index = gr.State([])
+
+    gr.HTML('<div style="font-size:12pt; text-align:center; color:yellow;">MNIST 分類器</div>')
+
+    model = gr.Radio(["detr-resnet-50", "detr-resnet-101"], value="detr-resnet-50")
+
+    with gr.Row():
+        input_image = gr.Image(label="", type="pil")
+        output_image = gr.Image(type="pil")
+    
+
+    threshold = gr.Slider(0, 1.0, value=0.9, label='threshold')
+
+    send_btn = gr.Button("予測する")
+    send_btn.click(fn=infer, inputs=[model, threshold, input_image], outputs=[output_image])
+
+#demo.queue()
+demo.launch(debug=True)
+
+
+
+
+### EOF ###