Issues
- 1
- 0
- 0
Your notebook tried to allocate more memory than is available. It has restarted.
#39 opened by Eyantra698Sumanto - 1
network problems
#38 opened by songbohui - 0
- 12
oscar_split_ViT-B_32_train_512.pkl文件的来源
#27 opened by masaiaaaa - 4
更换数据集问题
#3 opened by Leng-bingo - 12
pkl文件相关问题
#5 opened by Leng-bingo - 0
Release of predicted caption length
#36 opened by baaaad - 5
- 9
Set batchsize
#29 opened by songbohui - 10
关于第一轮结束之后,关于java的报错问题(用五个卡跑的,java问题报错后, watch -n 2 --color gpustat --c显示还有四个卡在跑)
#34 opened by Markkk111 - 2
How many parameters of your models?
#33 opened by ShyFoo - 3
请问如何进行测试
#32 opened by asasdsadagweh - 5
On length prediction accuracy results in your paper
#31 opened by xipq - 1
Any formula for q_pred function ?
#25 opened by linmou - 7
Beam search
#30 opened by vinevix - 2
Where is the code for the inference stage
#28 opened by xidian2wuzhaoji - 1
- 6
alpha_schedule问题
#24 opened by Iriya99 - 1
Can I train this model on Flickr30k?
#23 opened by vinevix - 2
What is the effect of the prefix_length?
#22 opened by ShyFoo - 1
请问如何使用 caption 测评代码?
#21 opened by verigle - 31
CosineLRScheduler 没有t_mul 参数
#9 opened by verigle - 0
Why is there no coco test dataset?
#20 opened by ShyFoo - 1
Using different loss
#19 opened by vinevix - 11
epoch 10开始loss都为NaN
#16 opened by ontheway-arch - 1
How to use one GPU for training.
#18 opened by shenyiyangsyy - 1
I trained the model throughout 30 epochs, how can I just test it predicting captiong for 1 image?
#17 opened by vinevix - 10
- 6
- 9
- 2
- 2
train_tclip.py文件问题
#11 opened by Leng-bingo - 20
batchsize问题
#7 opened by Leng-bingo - 2
tmp-results-{}.json 保存问题 写入文件与保存文件位置不一致
#10 opened by verigle - 2
environment.yml 文件是正确 的吗?可以重新导出环境的配置文件吗?
#8 opened by verigle - 0
batch
#6 opened by Leng-bingo - 2
关于self.bos_embedding的一些疑问
#4 opened by benboerbababoerben - 4
运行程序问题
#2 opened by Leng-bingo - 8