ghost
commented
6 years ago 因为不在同一路径所以出错，刚刚已解决
Closed ghost closed 6 years ago
ghost
commented
6 years ago 因为不在同一路径所以出错，刚刚已解决
bhr001
commented
5 years ago @DLstudent，这个不同路径是什么和什么不同路径？我也遇到这个问腿了，搞不定
bhr001
commented
5 years ago 因为不在同一路径所以出错，刚刚已解决
兄弟，什么和什么路径不同啊？我也遇到这个问题了，搞不定啊
TachibanaYoshino
commented
5 years ago 因为不在同一路径所以出错，刚刚已解决
兄弟，什么和什么路径不同啊？我也遇到这个问题了，搞不定啊
抱歉，我回复晚了，晚了十来天！我不知道你解决这个问题了没有啊，我呢当时是在终端运行的python experiments/SiamFC-3s-color-pretrained.py 。这时你要注意当前运行的文件主路径时./。所以你的预训练模型最好要按这个 matpath="./assets/2016-08-17.net.mat"路径给出，最好用绝对路径。而当你在pycharm中运行SiamFC-3s-color-pretrained.py 时，这时当前运行主路径就是./experiments/。所以你的预训练模型的文件路径要是上一层目录中的"assets/2016-08-17.net.mat"，即在前面加../ matpath="../assets/2016-08-17.net.mat"。 懂了吗？我很早就对这个跟踪做了运行，改进等尝试，当然现在已经换了方向了。孪生-fc这个不好改进，没有太大的提升。现在你多关注一下孪生RPN，孪生rpn++。商汤的算法
出错提示如下： Traceback (most recent call last): File "/home/cc/桌面/SiamFC-TensorFlow-master/experiments/SiamFC-3s-color-pretrained.py", line 32, in
'--enforce_clean': False,
File "/home/cc/anaconda3/lib/python3.6/site-packages/sacred/experiment.py", line 199, in run
run()
File "/home/cc/anaconda3/lib/python3.6/site-packages/sacred/run.py", line 229, in call
self.result = self.main_function(args)
File "/home/cc/anaconda3/lib/python3.6/site-packages/sacred/config/captured_function.py", line 48, in captured_function
result = wrapped(args, kwargs)
File "/home/cc/桌面/SiamFC-TensorFlow-master/scripts/convert_pretrained_model.py", line 64, in main
model.build()
File "/home/cc/桌面/SiamFC-TensorFlow-master/siamese_model.py", line 209, in build
self.setup_embedding_initializer()
File "/home/cc/桌面/SiamFC-TensorFlow-master/siamese_model.py", line 193, in setup_embedding_initializer
'convolutional_alexnet/', 'detection/')
File "/home/cc/桌面/SiamFC-TensorFlow-master/utils/train_utils.py", line 163, in load_mat_model
params = get_params_from_mat(matpath)
File "/home/cc/桌面/SiamFC-TensorFlow-master/utils/train_utils.py", line 70, in get_params_from_mat
netparams = sio.loadmat(matpath)["net"]["params"][0][0]
File "/home/cc/anaconda3/lib/python3.6/site-packages/scipy/io/matlab/mio.py", line 141, in loadmat
MR, file_opened = mat_reader_factory(file_name, appendmat, kwargs)
File "/home/cc/anaconda3/lib/python3.6/site-packages/scipy/io/matlab/mio.py", line 64, in mat_reader_factory
byte_stream, file_opened = _open_file(file_name, appendmat)
TypeError: 'NoneType' object is not iterable
很明显是sio.loadmat()在执行时，产生某种意外错误。或许是跟 '--enforce_clean': False,这个参数有关。但当我新建一个脚本单独运行： import scipy.io as sio matpath="assets/2016-08-17.net.mat" netparams = sio.loadmat(matpath)["net"]["params"][0][0] print(type(netparams)) 结果正常，并未报错。 所以想问下您这是什么情况？感觉非常奇怪？