Natural-Language-Object-Retrieval-tensorflow
Natural-Language-Object-Retrieval-tensorflow copied to clipboard
Implement Natural Language Object Retrieval in tensorflow
I keep getting this error CXX .build_release/src/caffe/proto/caffe.pb.cc AR -o .build_release/lib/libcaffe.a LD -o .build_release/lib/libcaffe.so /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/ranlib: file: .build_release/lib/libcaffe.a(cudnn_pooling_layer.o) has no symbols /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/ranlib: file: .build_release/lib/libcaffe.a(cudnn_conv_layer.o) has no symbols /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/ranlib: file: .build_release/lib/libcaffe.a(cudnn_tanh_layer.o) has no...
File "./exp-referit/cache_referit_local_features.py", line 12, in from captioner import Captioner ImportError: No module named captioner What module is captioner?
Does the lines [here](https://github.com/andrewliao11/Natural-Language-Object-Retrieval-tensorflow/blob/master/train.py#L197-L201) mean loading weights from pretrained model from LRCN?
Here, I want to ask what version of tensorflow the project is based on? Some syntax like tf.concat in [here](https://github.com/andrewliao11/Natural-Language-Object-Retrieval-tensorflow/blob/master/train.py#L117) is wrong in recent tensorflow version.