我在Mac上的Ubuntu 16.04 Parallels桌面上运行Google的tensorflow对象检测API的jupyter笔记本。我想测试其中一个非默认模型(即不使用Mobilenet的SSD),以查看边界框在对象检测任务中的准确度可能会发生变化。Tensorflow对象检测API运行模型动物园模型的问题
我在笔记本上改变了部分的模型准备如下:
# What model to download.
MODEL_NAME = 'ssd_mobilenet_v1_coco_11_06_2017'
MODEL_NAME = 'ssd_inception_v2_coco_11_06_2017'
MODEL_NAME = 'rfcn_resnet101_coco_11_06_2017'
#MODEL_NAME = 'faster_rcnn_resnet101_coco_11_06_2017'
#MODEL_NAME = 'faster_rcnn_inception_resnet_v2_atrous_coco_11_06_2017'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')
NUM_CLASSES = 90
我然后跳转到执行加载的冷冻Tensorflow模型到内存单元。不幸的是,如果我尝试任何过去的3款车型(rfcn_resnet101_coco_11_06_2017,faster_rcnn_resnet101_coco_11_06_2017,faster_rcnn_inception_resnet_v2_atrous_coco_11_06_2017),在Firefox中的笔记本电脑死机的,我得到了以下错误消息:
The kernel appears to have died. It will restart automatically.
所以我无法测试出最后3种型号即使我已经下载了tar.gz文件并将它们提取到了object_detection文件夹中。有人能解释我可能做错了什么吗?
谢谢你的时间!
这可能是一个内存问题吗? –