Closed JoshSmith0118 closed 2 years ago
thanks for your reply, I did as you said, but the result still as follow:
/Users/shihaozhe/R2GenCMN-main/modules/caption_model.py:73: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
beam_ix = ix // vocab_size # Nxb which beam
{'testlen': 7517, 'reflen': 10304, 'guess': [7517, 7221, 6925, 6629], 'correct': [4286, 1655, 875, 503]}
ratio: 0.7295225155278795
Traceback (most recent call last):
File "/Users/shihaozhe/R2GenCMN-main/main_train.py", line 136, in
Java 1.8.0 is needed for METEOR. Please install it.
Thanks a lot, the problem has been solved.
hi thx for your code, but when I run your code on my m1 mac by CPU, I stuck in there BrokenPipeError: [Errno 32] Broken pipe then I google it, and someone said it might be the num_workers problem. https://blog.csdn.net/qq_33666011/article/details/81873217 Do you know how to solve this problem? thanks for your attention