Andrew
Andrew
Hello. I have trained ResNet101. I wonder how to choose an appropriate trained model? I got train accuracy almost100%. The highest test accuracy reached 95.930% when 299 epoch, and 99.984%...
Hello. I have read your paper, it's great. I have test the result of the experiments on "ImageNet&untarget attack", but the success_rate is only 0.525. Is there anything wrong? I...
## Settings model: damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch sv_threshold: 0.6 ## Scene 1. Same person audio_in: ( 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_enroll.wav', 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_same.wav' ) model_scores: [0.9804788827896118, 0.019521117210388184] 2. Different person audio_in=( 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_enroll.wav', 'https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/sv_example_different.wav') ) model_scores: [0.7429116070270538, 0.25708839297294617] ##...
Hi 作者大大，我这里自己生成了上万条文字数据，想对这个文字数据合成图片数据。目前尝试使用一部分预料数据（10条）来生成，目前看速度非常慢，请问是什么问题呢？最后一直卡住了。 执行命令：python main.py --corpus_dir=corpus_dir --corpus_mode=list --gpu 程序输出： ``` Total fonts num: 1 Background num: 1 Loading corpus from: corpus_dir Load corpus: corpus_dir/com_dataset_part.txt Total lines: 10 Generate text images in...
Hi 作者大大。我这边有个图片文字识别场景，需要识别的图片中部分文字包含特殊字符，这块能否通过在预训练模型的基础上微调来实现识别特殊字符呢？如果可以，可否提供微调的教程或者建议呢？感谢。
Hello. Can you release your adv training result and training detail on CIFAR-10?
Hi, I think it would be helpful if router chain is supported in this great project. Router chain is LLMChain that acts as router, simillar to: [https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/chains/router/multi_prompt.py](url)