本文整理汇总了Python中preprocessor.Preprocessor.set_tfidf方法的典型用法代码示例。如果您正苦于以下问题：Python Preprocessor.set_tfidf方法的具体用法？Python Preprocessor.set_tfidf怎么用？Python Preprocessor.set_tfidf使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类preprocessor.Preprocessor的用法示例。
在下文中一共展示了Preprocessor.set_tfidf方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: ImageServer
# 需要导入模块: from preprocessor import Preprocessor [as 别名]
# 或者: from preprocessor.Preprocessor import set_tfidf [as 别名]
class ImageServer(SocketServer.ThreadingTCPServer):
""" Generates a caption from an image """
def __init__(self, server_address, RequestHandlerClass, args):
SocketServer.ThreadingTCPServer.__init__(self, server_address, RequestHandlerClass)
self.options_file = args.options
self.model = args.model
print "Loading options..."
self._load_options()
self._load_capgen()
if "tex_dim" in self.options:
print "Loading text preprocessor..."
self._load_text_preprocessor(args)
print "Loading dictionary..."
self._load_worddict()
print "Loading CNN..."
self._load_cnn()
print "Loading model..."
self._build()
self._update_status(5)
print "All done!"
def _update_status(self, status):
"""
0: not running
1: loading_options
2: loading dictionary
3: loading CNN
4: building model
5: done
6: loading preprocessor
"""
json.dump({"status": status}, open("{}_runningstatus.json".format(self.model), "w"))
def _load_options(self):
""" Loads the options of the caption model """
self._update_status(1)
with open(self.options_file, "rb") as f:
self.options = pkl.load(f)
def _load_capgen(self):
""" Loads the caption generator version dependent on whether to use textual context or not """
if "tex_dim" in self.options:
import capgen_text as capgen
self.capgen = capgen
else:
import capgen
self.capgen = capgen
def _load_worddict(self):
""" Load the worddict """
self._update_status(2)
self.dictionary = dict()
for kk, vv in self.options["dictionary"].iteritems():
self.dictionary[vv] = kk
self.dictionary[0] = "<eos>"
self.dictionary[1] = "UNK"
def _load_text_preprocessor(self, args):
""" Load the preprocessor for the context """
self._update_status(6)
self.text_preprocessor = Preprocessor()
# Load preprocessors based on type of model
## TF-IDF:
if "tfidf" in self.options["preproc_type"]:
print "Loading TF-IDF model..."
with open(args.tfidfmodel, "rb") as f_tfidf, open(args.svdmodel, "rb") as f_svd:
tfidf_model = pkl.load(f_tfidf)
svd_model = pkl.load(f_svd) if "with_svd" in self.options["preproc_params"] else None
self.text_preprocessor.set_tfidf(tfidf_model, svd_model)
## Word2Vec:
if "w2v" in self.options["preproc_type"]:
print "Loading Word2Vec model..."
w2v_model = Word2Vec.load_word2vec_format(args.w2vmodel, binary=True)
self.text_preprocessor.set_w2v(w2v_model)
## Raw:
if "raw" in self.options["preproc_type"]:
print "Loading counter model..."
with open(args.rawmodel, "rb") as f_raw:
raw_model = pkl.load(args.rawmodel)
self.text_preprocessor.set_raw(raw_model)
def resize_image(self, image, resize=256, crop=224):
""" Resizes and crops the image """
# From author Kelvin Xu:
# https://github.com/kelvinxu/arctic-captions/blob/master/alpha_visualization.ipynb
width, height = image.size
if width > height:
width = (width * resize) / height
height = resize
#.........这里部分代码省略.........