when I use the code to evaluate BLEU/METEOR/CIDEr scores,I failed!

[Afeihan]

when I use the following command to run the code,I failed

  th eval.lua -model model_id1-501-1448236541.t7 -num_images 1000 -language_eval 1

The error message as follows:

index created!
tokenization...
Traceback (most recent call last):
File "myeval.py", line 32, in
cocoEval.evaluate()
File "/home/gu/neuraltalk2-master/coco-caption/pycocoevalcap/eval.py", line 31, in evaluate
gts = tokenizer.tokenize(gts)
File "/home/gu/neuraltalk2-master/coco-caption/pycocoevalcap/tokenizer/ptbtokenizer.py", line 52, in tokenize
stdout=subprocess.PIPE)
File "/usr/lib/python2.7/subprocess.py", line 710, in init
errread, errwrite)
File "/usr/lib/python2.7/subprocess.py", line 1327, in _execute_child
raise child_exception
OSError: [Errno 2] No such file or directory

Can i get some relevant advice on how to solve this ?

[zzy-ucas]

@Afeihan I have met the same problem in https://github.com/metrofun/AdaptiveAttention and tried many ways. The reason is that the tool used in command cmd in

    cmd = ['java', '-cp', STANFORD_CORENLP_3_4_1_JAR, 'edu.stanford.nlp.process.PTBTokenizer', '-preserveLines', '-lowerCase']

is not installed. So the FILE NOT FOUND is the TOOL java and cause the error here in

p_tokenizer = subprocess.Popen(cmd, cwd=path_to_jar_dirname, stdout=subprocess.PIPE)

Hope this may help U!