bruce1408
bruce1408
> line 70: **index = randint(0, vocab_size - 1) # random index in vocabulary.** > I think the replace index can't involve 'cls' ,'sep' and 'mask'! Yes， it`s right. so...
download the file 'download_datasets.py',and then open it,you will find a nota '# the original google drive link at https://drive.google.com/file/d/0B0ywwgffWnLLcms2WWJQRFNSWXM/view'。So this Url is the access to download file 'the flowers_text_c10'.
merge update
use this ```from sklearn.neighbors import KernelDensity```
**SET CUDA TRUE To use GPU!** ### envs - 2080ti x 1 - ubuntu 16.04 - python 3.6 - pytorch 1.5.0 - cpu cores :8 - cpu processor num :16...
merge & update
> 修改189行的`get_labels`函数即可 你说的是tensorflow的189行还是pytorch？并没有发现get_labels函数.
> Hi, version of colab is PyTorch1.5.0, I modified detection.py and ssd.py. > so that it works without warning and error. > > Since detection.py have torch.autograd.Function, I delete def...
you should better change you data path to D:\ or another disk.
The model download link is here https://drive.google.com/file/d/1krOLgjW2tAPaqV-Bw4YALz0xT5zlb5HF/view?pli=1