（已開源）5行代碼，快速實現圖像分割，逐行詳解，手誘教你處理圖像 [PixelLib]

資料來源:https://mp.weixin.qq.com/s/WCrwVMnwtyZ96oUeBti4Ew

文字摘要:

    安裝最新版本的 TensorFlow、Pillow、OpenCV-Python、scikit-image 和 PixelLib：

        pip3 install tensorflow
        pip3 install pillow
        pip3 install opencv-python
        pip3 install scikit-image
        pip3 install pixellib

    PixelLib 實現需求分區

        import pixellib
        from pixellib.semantic import semantic_segmentation
        segment_image = semantic_segmentation()
        segment_image.load_pascalvoc_model(“deeplabv3_xception_tf_dim_ordering_tf_kernels.h5”)
        segment_image.segmentAsPascalvoc(“path_to_image”, output_image_name = “path_to_output_image”)

    

    實戰！(圖片文件命名為：sample1.jpg)

        import pixellib
        from pixellib.semantic import semantic_segmentation
        segment_image = semantic_segmentation()
        segment_image.load_pascalvoc_model(“deeplabv3_xception_tf_dim_ordering_tf_kernels.h5”)
        segment_image.segmentAsPascalvoc(“sample1.jpg”, output_image_name = “image_new.jpg”)    

    可以通過修改下面的代碼，來檢查執行分割的推理時間

        import pixellib
        from pixellib.semantic import semantic_segmentation
        import time
        segment_image = semantic_segmentation()
        segment_image.load_pascalvoc_model(“pascal.h5”)
        start = time.time()
        segment_image.segmentAsPascalvoc(“sample1.jpg”, output_image_name= “image_new.jpg”)
        end = time.time()
        print(f”Inference Time: {end-start:.2f}seconds”)

        

    PixelLib在執行實例分割時，基於的框架是Mask RCNN，代碼如下：

        import pixellib
        from pixellib.instance import instance_segmentation
        segment_image = instance_segmentation()
        segment_image.load_model(“mask_rcnn_coco.h5”)
        segment_image.segmentImage(“path_to_image”, output_image_name = “output_image_path”)

        

    上圖，實戰第二彈！

        import pixellib
        from pixellib.instance import instance_segmentation
        segment_image = instance_segmentation()
        segment_image.load_model(“mask_rcnn_coco.h5”)
        segment_image.segmentImage(“sample2.jpg”, output_image_name = “image_new.jpg”)    

        
    也可以通過同樣的代碼查詢實例片段的推理時間：

        import pixellib
        from pixellib.instance import instance_segmentation
        import time
        segment_image = instance_segmentation()
        segment_image.load_model(“mask_rcnn_coco.h5”)
        start = time.time()
        segment_image.segmentImage(“former.jpg”, output_image_name= “image_new.jpg”)
        end = time.time()
        print(f”Inference Time: {end-start:.2f}seconds”)  

完整圖文