ydyrx
ydyrx
Hi, Thanks for the excellent code base. can i get the feature trained with faster rcnn and backbone resnet152? I'm waiting for your reply.
Hi, Thanks for the excellent code base. can i get the feature trained with resnet152? In short, Faster RCNN was trained with Resnet152 as the backbone network. I look forward...
Hi, Thanks for the excellent code base. can i get the feature trained with faster rcnn and backbone resnet152? I'm waiting for your reply.
Hi, Thanks for the excellent code base. can i get the feature trained with faster rcnn and backbone resnet152? I'm waiting for your reply.
Hi, Thanks for the excellent code base. can i get the feature trained with faster rcnn and backbone resnet152? I'm waiting for your reply.
您好呀，当我准备flickr30k的数据集的图像特征时，出现了这个错误： ``` Traceback (most recent call last): File "scripts/prepro_feats.py", line 101, in main(params) File "scripts/prepro_feats.py", line 64, in main I = skimage.io.imread(os.path.join(params['images_root'], img['filepath'], img['filename'])) KeyError: 'filepath' ``` 请问一下您这是什么原因呢？是不是因为flickr30k没分train和val？
您好，我使用了flickr8k训练，也是可以完成成功地进行训练。但在最后的eval阶段出现了以下错误： image 7989: a man in a black shirt is riding a rope image 7990: a group of football players in red uniforms in the field image 7991: a brown...
您好，我想生成一些train_loss的曲线图，请问您的代码有提供吗？或者您有什么建议？
您好，我新环境进行eval时出现了这个问题，请问是哪一步出现问题了，我没安装那个包呢？谢谢您。 Traceback (most recent call last): File "tools/eval.py", line 74, in lang_stats = eval_utils.language_eval(opt.input_json, predictions, n_predictions, vars(opt), opt.split) File "/home/yuanling/final_work/ImageCaptioning.pytorch/captioning/utils/eval_utils.py", line 85, in language_eval cocoEval = COCOEvalCap(coco, cocoRes) NameError: name...
您好，抱歉我用中文问您问题。我想修改一下您的模型，比如我想修改updown模型，请问我应该在那个文件.py修改模型呢？我的想法是ImageCaptioning.pytorch-master\captioning\models\AttModel.py里面的这个部分？ `class UpDownCore(nn.Module): def __init__(self, opt, use_maxout=False): super(UpDownCore, self).__init__() self.drop_prob_lm = opt.drop_prob_lm self.att_lstm = nn.LSTMCell(opt.input_encoding_size + opt.rnn_size * 2, opt.rnn_size) # we, fc, h^2_t-1 self.lang_lstm = nn.LSTMCell(opt.rnn_size * 2, opt.rnn_size)...