cloudfool
cloudfool
> I think `train_prompts.py` is the last step. As for the first step, it doesn't seem to be provided in the code and is introduced as a pre-trained model in...
> Thank you for your feedback, and sorry about late reply. And in /applications/ChatGPT)/examples/ ,we have 3 examples : train_dummy -> show the vanilla way to start **training step 3**....
> python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 48, 320" --rec_char_dict_path="your text dict path" 检查一下是不是模型和字典不匹配 我觉得应该没问题，跑其他图片都是可以的； 你要不帮我测试一下这两张 看看是不是和我的识别结果相同？
So it must be used under torch1.13? Do you know any other ways to solve this problem?
exactly
I also found another problem in retinanet.py gt_classes, gt_anchors_reg_deltas = self.get_ground_truth(anchors, gt_instances), which "get_ground_truth" is not implemented
重发了，请check一下
> 没有了，没有了，我差不多改好了，精度又提升了一点点 请问 具体是如何做的呢？
> 那不可以噢，需要优化代码了，你没法表示一段文字是什么token，需要改成一个span的所有token的embedding聚合成一个span的embedding作为输入 请问如何聚合成一个span的embedding？ 谢谢