0
我使用它實現所謂的更快R-CNN一個深度學習模型tensorflow以下GitHub的倉庫,我想:錯誤以便更快地-R-CNN培訓模式在Tensorflow,但Caffe實施
https://github.com/smallcorgi/Faster-RCNN_TF
然後,我運行命令(我想只能用CPU來運行):
python ./tools/demo.py --model VGGnet_fast_rcnn_iter_70000.ckpt
我得到的錯誤:
Traceback (most recent call last):
File "./tools/demo.py", line 11, in <module>
from networks.factory import get_network
File "/home/brm17/Faster-RCNN_TF/tools/../lib/networks/__init__.py", line 8, in <module>
from .VGGnet_train import VGGnet_train
File "/home/brm17/Faster-RCNN_TF/tools/../lib/networks/VGGnet_train.py", line 2, in <module>
from networks.network import Network
File "/home/brm17/Faster-RCNN_TF/tools/../lib/networks/network.py", line 3, in <module>
import roi_pooling_layer.roi_pooling_op as roi_pool_op
File "/home/brm17/Faster-RCNN_TF/tools/../lib/roi_pooling_layer/roi_pooling_op.py", line 5, in <module>
_roi_pooling_module = tf.load_op_library(filename)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/load_library.py", line 64, in load_op_library
None, None, error_msg, error_code)
tensorflow.python.framework.errors_impl.NotFoundError: /home/brm17/Faster-RCNN_TF/tools/../lib/roi_pooling_layer/roi_pooling.so: undefined symbol: _Z22ROIPoolBackwardLaucherPKffiiiiiiiS0_PfPKiRKN5Eigen9GpuDeviceE
是什麼問題,以及如何解決這個問題?
問題是,您沒有按照存儲庫中的說明。 –
歡迎來到StackOverflow。請刪除標記'caffe',因爲它不相關。 – lnman