WeakVRD-Captioning icon indicating copy to clipboard operation
WeakVRD-Captioning copied to clipboard

Implementation of paper "Improving Image Captioning with Better Use of Caption"

Results 4 WeakVRD-Captioning issues
Sort by recently updated
recently updated
newest added

I am trying to reproduce your model for weak supervised multi instance learning, I am a bit confused about the formation of positive and negative bag. It says in the...

当我尝试CIDEr优化训练时,遇到报错:“ gen_result, sample_logprobs, core_args = decoder(vrg_data, fc_feats, att_feats, weak_relas, att_masks, opt={'sample_max': 0, 'return_core_args': True}, mode='sample') ValueError: need more than 2 values to unpack” decoder()只能返回gen_result和sample_logprobs,不能返回core_args. 我想问一下,decoder()的返回值具体由那一步决定???

作者您好!十分感谢您的工作,想请问您是否可以提供一下COCO评估服务器的测试数据集的coco_cmb_vrg文件,万分感激您!