Leo
Leo
same problem!
BLEU method is one of the methods to evaluate the performance of the model. The training process can ensure that the loss value decreases steadily, but the BLEU value is...
In order to test my ideas and dispel your confusion, I have made some progress. I changed the network structure: after the merge layer, two full connection layers were added,...
Here is the part of the function that needs to be changed. To test the performance of different models, I changed the structure several times, so I'm not sure that...
I'm afraid I can't give you much help because my major is not very relevant to machine learning. It's just a hobby for me to do this. If you don't...
Occasionally read some pages, run the code on them, or spend some time reading papers, that's all. Best Regards.
You're welcome. I hope you can make a success in Image Captioning. Best Regards :)
@1228589545 features.pkl 这个文件是运行完 step1之后生成的，要获得这个文件需要你自己运行的
1.原文说分开训练是因为网络难以训练。我更改了输入尺寸，计算压力变小了。不分开训练同样可以把网络训练得很好。 2.没有对比同时训练和分开训练的效果差异，因为没必要。 3.你的第二个问题，我猜你是想问 dec_conv1 = concatenate([seg_conv4,seg_output],axis=3) 这一步直接把两者拼接起来是否合适。 其实原文中提出把这两者连接在一起就很奇怪，就说 channel 的比例（原文1024:1）就注定mask的权重很小。如果你觉得不妥，可以在 mask 后添加卷积层扩充 channel。 4.另，效果更好的语义分割模型还有 FCN、ENet、DeepLab、PSPNet、ERFNet等。