VAC_CSLR
VAC_CSLR copied to clipboard
Visual Alignment Constraint for Continuous Sign Language Recognition. ( ICCV 2021)
Hello, could you provide the process and evaluation scripts of CSL dataset?
实验复现结果不一致
作者您好,我们通过下载您的代码并对您提出的VAC进行了重跑了50个epoch(没有使用BN),结果最好只有35.1%的词错率。此外,我们调整代码中的权重,对baseline算法进行实验(不使用BN),发现结果也与论文中结果相差甚多,请问是否代码版本不一致,又或我们训练时间过短?
Hello, Thank you for the awesome work. I am trying to use the model on another dataset, so I figure I should structure my data accordingly to the format of...
Can you explain why you need to use preprocess.sh to process the predicted result?
Fix the problem that opencv-python reads and saves files incorrectly when the dataset is placed in the Chinese path
What are the video augmentation options used in the pre-trained model ([[Dropbox]](https://www.dropbox.com/s/zbas78emfz5m4bp/resnet18_slr_pretrained_distill25.pt?dl=0)) ? In the code I can see that these are the ones uncommented, is that the case for...
I ran your code and found the following error, where are the parameters put into the GPU? --------------------------------------------------------------------------------------------------------------------------------------------------- Traceback (most recent call last): File "main.py", line 218, in processor.start() File...
hello, i get an error on the training phase The loss is decreasing but when i evaluate the model it doesn't recognize any word i get 100 always. i install...
hello, how are guys i try this code but my machine don't have GPU service enabled So, please give me the solution how to try with out CUDA the error...