jchenghu/ExpansionNet_v2
Implementation code of the work "Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning"
PythonMIT
Issues
- 1
- 3
I take the liberty of bothering you again to ask how to visualize attention in the same way as your paper Fig.4, thanks!
#25 opened by qqq-gif - 17
how long it takes to run test.py on a 3060
#23 opened by qqq-gif - 8
Hi, I actually have a question, why is the swin transformer fine-tuned during training, but the parameters of the final model remove the parameters of the swin-transformer?
#22 opened by PanYuQi66666666 - 2
online testing CUDA overflow
#21 opened by PanYuQi66666666 - 1
- 2
Hello,I have a question
#17 opened by PanYuQi66666666 - 2
- 3
- 2
Hello, if I want to view multiple descriptions generated by the final beam search strategy for the same image, in which code should I output this?
#16 opened by PanYuQi66666666 - 17
GPU、MSCOCO、CIDER
#13 opened by qqq-gif - 15
Fine-tune on Custom Dataset
#12 opened by JFcy - 6
- 3
- 5
Hello, can you provide a code for measuring the number of model parameters?
#11 opened by PanYuQi66666666 - 43
Convert to ONNX then to TensorRT format
#2 opened by shahizat - 12
CUDA OUT OF MEMORY DURING THE TRAINING ! I USE THE NVIDIA A10 ,24G MEMORY.BATCH_SIZE:4.
#9 opened by PanYuQi66666666 - 3
hi, i meet some trouble when i want to use ensemble test , Please help me!! thanks!
#10 opened by PanYuQi66666666 - 5
hello,I'd like to know approximately how much computing power is required for training code?
#8 opened by PanYuQi66666666 - 12
Training on Custom Dataset
#5 opened by ChandanVerma - 9
Zero scores during evaluation
#6 opened by jchenghu - 3
why is the path set when i=1?
#7 opened by x921338983 - 1
Errors when running demo.py
#3 opened by ashaychangwani - 2
- 4