1. 程式人生 > >zero-shot object detection

zero-shot object detection

推薦搭配套餐:

  • Python 2.7
  • Keras 2.1.4
  • OpenCV 2.4.13
  • Tensorflow 1.3.0

或者:

  • Python 3.5-3.6
  • Keras 2.0.8
  • OpenCV 3.4.0
  • Tensorflow 1.3.0

 

安裝:

1 本人套餐:

NVIDIA-SMI 384.130

CUDA Version 8.0.61

CUDNN_VERSION 6.0.21

pip install keras==2.1.4
pip install tensorflow-gpu==1.3.0
pip install opencv-python

 

2 下載h5格式的預訓練檔案,放入model資料夾:

https://www.dropbox.com/s/v6ueoa1g19bddao/model_frcnn.hdf5?dl=0

網頁需要翻qiang下載,或者百度雲下載:

連結: https://pan.baidu.com/s/1ZORTuXEoTNQHYkslLQW9vA    提取碼: 5tui 

 

3 執行:

執行detect.py 批量檢測Dataset/Sampleinput下的圖片,輸出圖片在Dataset/Sampleoutput

 

問題 1:

ImportError: libcublas.so.9.0: cannot open shared object file: No such file or directory


Failed to load the native TensorFlow runtime.


解決:

這是因為我裝了tensorflow-gpu 1.5版本,而我用的是cuda 8.0和cudnn6.0,1.5版本要求cuda 9.0,我的做法就是回滾:

 

pip install tensorflow-gpu==1.3.0

問題 2:

File "/home/thu/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/common_shapes.py", line 659, in _call_cpp_shape_fn_impl
    raise ValueError(err.message)
ValueError: Shape must be rank 1 but is rank 0 for 'bn_conv1/Reshape_4' (op: 'Reshape') with input shapes: [1,1,1,64], [].


解決:

pip install keras==2.1.4

 

問題 3:

OSError: Unable to open file (Unable to open file: name = 'model/model_frcnn.hdf5', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)


解決:

下載h5格式的預訓練檔案,放入model資料夾:

https://www.dropbox.com/s/v6ueoa1g19bddao/model_frcnn.hdf5?dl=0

網頁需要翻qiang下載,或者百度雲下載:

連結: https://pan.baidu.com/s/1ZORTuXEoTNQHYkslLQW9vA    提取碼: 5tui 

 

 

 

Ref: https://github.com/salman-h-khan/ZSD_Release