AlbertMa123
AlbertMa123
me too, when i used lr=20, then the loss was very strange and crazy......
i have the same confusion
it is a point. But it is not a problem. I guess
我跑了30轮，loss是2.3590，下降很慢啊
应该是pytorch版本升级导致的问题，最后一次order，order=tensor(25)（例如），此时shape=[]，即不能用order[0]来获取第一个元素，建议这么写： if order.dim()==0: order = order.reshape(-1)
我也是这样的显示，在pycharm的输出框里等了很久才打印检测结果，耗时200+秒，性能差一点的电脑直接退出运行 出现Creating model: ('PP-OCRv5_server_det', None) Using official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /home/xxxyyy/.paddlex/official_models.，其原因估计是没有找到模型，但实际上应该是找到了的，因为最终200+秒后打印了检测结果，想要不出现这个提示，可以在PaddleOCR里指定模型路径，比如我写的是： ocr = PaddleOCR( doc_orientation_classify_model_name='PP-LCNet_x1_0_doc_ori',...... 出现UserWarning: No ccache found. Please be...
Hi, I saw your issue by chance, I studied transformer a little and use it to do word_language_model once which was not successful...... 1. why dont use transformer-decode in word_language_model?...