RCNN

[wangzeng1992]

Python or MATLAB version (for pycaffe and matcaffe respectively): Traceback (most recent call last): File "D:/VS2013/caffe/caffe-master/Build/x64/Release/pycaffe/detect.py", line 97, in <module> detect(pretrained_model, model_def, mean_file, input_file) File "D:/VS2013/caffe/caffe-master/Build/x64/Release/pycaffe/detect.py", line 62, in detect predictions_df = pd.DataFrame(np.vstack(spec_df.prediction.values), columns=labels_df['name']) File "D:\Anaconda\lib\site-packages\pandas\core\frame.py", line 306, in __init__ copy=copy) File "D:\Anaconda\lib\site-packages\pandas\core\frame.py", line 483, in _init_ndarray return create_block_manager_from_blocks([values], [columns, index]) File "D:\Anaconda\lib\site-packages\pandas\core\internals.py", line 4303, in create_block_manager_from_blocks construction_error(tot_items, blocks[0].shape[1:], axes, e) File "D:\Anaconda\lib\site-packages\pandas\core\internals.py", line 4280, in construction_error passed, implied)) ValueError: Shape of passed values is (200, 1673), indices imply (1000, 1673) Who can help me?? how can i fix it? thanks very much!

[wadefelix]

你的shape对不上啊。 检查prototxt，检查batchsize等配置。 具体嘛，你提供的信息太少啊。

[Noiredd]

Please post usage, installation, or modeling questions, or other requests for help to the caffe-users list instead of Issues. This helps developers maintain a clear, uncluttered, and efficient view of the state of Caffe. Please read the guidelines for contributing before submitting an issue or a pull request.

Please make your request more readable when posting to the caffe-users list. Also describe more clearly what were you doing.