PSENet踩坑记录

使用的代码为PSENet的pytorch版，代码地址：https://github.com/whai362/PSENet

报错：ModuleNotFoundError: No module named 'cPickle' 打开/PSENet-master/util/io_.py，将import cPickle as pkl的CPickle改为pickle

报错：ModuleNotFoundError: No module named 'commands' commands是python2版本里的，在python3.0以上已经没有commands模块了，使用subprocess代替commands

报错：

File "XXX/PSENet-master/dataset/icdar2015_loader.py", line 12, in <module> import Polygon as plg

ModuleNotFoundError: No module named 'Polygon'

安装polygon ：pip install Polygon3

报错：ValueError: invalid literal for int() with base 10: '\ufeff232' 打开PSENet-master/util/io_.py，找到read_lines函数，将f = open(p,'r'）改为f = open(p,'r',encoding='utf-8-sig')

报错：

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

File "/home/zhangmingzhou1/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop

data = fetcher.fetch(index)

File "/home/zhangmingzhou1/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch

data = [self.dataset[idx] for idx in possibly_batched_index]

File "/home/zhangmingzhou1/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>

data = [self.dataset[idx] for idx in possibly_batched_index]

File "/home/zhangmingzhou1/PSENet-master/dataset/icdar2015_loader.py", line 196, in __getitem__

bboxes = np.reshape(bboxes * ([img.shape[1], img.shape[0]] * 4), (bboxes.shape[0], bboxes.shape[1] / 2, 2)).astype('int32')

File "<__array_function__ internals>", line 6, in reshape

File "/home/zhangmingzhou1/anaconda3/envs/pytorch/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 299, in reshape

return _wrapfunc(a, 'reshape', newshape, order=order)

File "/home/zhangmingzhou1/anaconda3/envs/pytorch/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 67, in _wrapfunc

return _wrapit(obj, method, *args, **kwds)

File "/home/zhangmingzhou1/anaconda3/envs/pytorch/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 44, in _wrapit

result = getattr(asarray(obj), method)(*args, **kwds)

TypeError: 'float' object cannot be interpreted as an integer

找到代码icdar2015_loader.py中的下段，“/”改为“//”，如下所示：

bboxes = np.reshape(bboxes * ([img.shape[1], img.shape[0]] * 4), (bboxes.shape[0], bboxes.shape[1] // 2, 2)).astype('int32')