我在Mac上的Ubuntu 16.04 Parallels桌面上運行Google的tensorflow對象檢測API的jupyter筆記本。我想測試其中一個非默認模型(即不使用Mobilenet的SSD),以查看邊界框在對象檢測任務中的準確度可能會發生變化。Tensorflow對象檢測API運行模型動物園模型的問題
我在筆記本上改變了部分的模型準備如下:
# 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
我然後跳轉到執行加載的冷凍Tensorflow模型到內存單元。不幸的是,如果我嘗試任何過去的3款車型(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中的筆記本電腦死機的,我得到了以下錯誤消息:
The kernel appears to have died. It will restart automatically.
所以我無法測試出最後3種型號即使我已經下載了tar.gz文件並將它們提取到了object_detection文件夾中。有人能解釋我可能做錯了什麼嗎?
謝謝你的時間!
這可能是一個內存問題嗎? –