Delete app.py

remove old app.py

app.py

@@ -1,69 +0,0 @@
-# -*- coding: utf-8 -*-
-"""appre.ipynb
-
-Automatically generated by Colaboratory.
-
-Original file is located at
-    https://colab.research.google.com/drive/1lDMgKpnES31ZrHV62ifeYr6k7KPvaPLt
-"""
-import torch
-import gradio as gr
-from transformers import Owlv2Processor, Owlv2ForObjectDetection
-import spaces
-
-# Use GPU if available
-if torch.cuda.is_available():
-    device = torch.device("cuda")
-else:
-    device = torch.device("cpu")
-
-model = Owlv2ForObjectDetection.from_pretrained("google/owlv2-base-patch16-ensemble").to(device)
-processor = Owlv2Processor.from_pretrained("google/owlv2-base-patch16-ensemble")
-
-@spaces.GPU
-#输入图像，搜索文本，检测分数
-def query_image(img, text_queries, score_threshold):
-    text_queries = text_queries
-    #分割搜索文本
-    text_queries = text_queries.split(",")
-    #转换为正方行torch矩阵
-    #（长宽边最大的那个设置为size）
-    size = max(img.shape[:2])
-    target_sizes = torch.Tensor([[size, size]])
-    #创建输入（搜索文本和图像转换为torch张量发送到GPU）
-    inputs = processor(text=text_queries, images=img, return_tensors="pt").to(device)
-    #禁用梯度计算，运行推理
-    with torch.no_grad():
-        outputs = model(**inputs)
-    #输出分数和边界框信息
-    outputs.logits = outputs.logits.cpu()
-    outputs.pred_boxes = outputs.pred_boxes.cpu()
-    #导出输出结果
-    results = processor.post_process_object_detection(outputs=outputs, target_sizes=target_sizes)
-    #分类存储输出结果的边界框，分数，标签
-    boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]
-    #
-    #创建空列表
-    result_labels = []
-    #遍历分类存储的输出结果
-    for box, score, label in zip(boxes, scores, labels):
-        #转换为整数
-        box = [int(i) for i in box.tolist()]
-        #过滤阈值以下的目标
-        if score < score_threshold:
-            continue
-        result_labels.append((box, text_queries[label.item()]))
-        result
-    num_result_labels = len(result_labels)
-    return img, result_labels
-
-
-
-demo = gr.Interface(
-    query_image,
-    inputs=[gr.Image(), "text", gr.Slider(0, 1, value=0.2)],
-    outputs=["annotatedimage"],
-    title="Zero-Shot Object Detection with OWLv2",
-)
-demo.launch()
-