feat: init

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.JPG filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.idea/

app.py

@@ -0,0 +1,87 @@
+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")
+
+
+import gradio as gr
+
+
+COLORS = ["#ff7f7f", "#ff7fbf", "#ff7fff", "#bf7fff",
+            "#7f7fff", "#7fbfff", "#7fffff", "#7fffbf",
+            "#7fff7f", "#bfff7f", "#ffff7f", "#ffbf7f"]
+
+fdic = {
+    "family" : "DejaVu Serif",
+    "style" : "normal",
+    "size" : 18,
+    "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_int = [i.item() for i in torch.round(box).to(torch.int32)]
+        x, y, w, h = box_int[0], box_int[1], box_int[2]-box_int[0], box_int[3]-box_int[1]
+        #x, y, w, h = torch.round(box[0]).item(), torch.round(box[1]).item(), torch.round(box[2]-box[0]).item(), torch.round(box[3]-box[1]).item()
+
+        ax.add_patch(plt.Rectangle((x, y), w, h, fill=False, color=selected_color, linewidth=3, alpha=0.8))
+        ax.text(x, y, f"{model_tiny.config.id2label[label.item()]}: {round(score.item()*100, 2)}%", fontdict=fdic, alpha=0.8)
+
+    plt.axis("off")
+
+    return plt.gcf()
+
+
+def infer(in_pil_img, in_threshold=0.9):
+    target_sizes = torch.tensor([in_pil_img.size[::-1]])
+
+    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
+    results = image_processor_tiny.post_process_object_detection(outputs, threshold=in_threshold, target_sizes=target_sizes)[0]
+
+    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
+
+
+with gr.Blocks(title="Object Detection") as demo:
+
+    with gr.Row():
+        input_image = gr.Image(label="Input image", type="pil")
+        output_image = gr.Image(label="Output image with predicted instances", type="pil")
+
+    gr.Examples(['samples/1.jpeg', 'samples/2.JPG'], inputs=input_image)
+
+    threshold = gr.Slider(0, 1.0, value=0.9, label='threshold')
+
+    send_btn = gr.Button("Infer")
+    send_btn.click(fn=infer, inputs=[input_image, threshold], outputs=[output_image])
+
+#demo.queue()
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,2 @@
+torch
+transformers[timm]