catsled

when i studied the "6. The tokenizers liabrary -- Unigram tokenization" , i couldn't understand the following why the P("pu") = 5/210, shouldn't it be the 17 / 210, because...

I think the `data/xxx.yaml` should be `configs/xxx.yaml`

Got stuck when train resnet50 with QAT

6

When I quantize a ResNet50 model and train it, it may get stuck at the first backward pass; it's normal when I train a non-quantized model.. GPU:A800 data:Cifar10  ...

Can I use quanto on AMD GPU?

3

Does quanto work with AMD GPUs ?

 does it should be args.height, args.width

If the result is generated using dreambooth_lora, it makes sense; however, if it is not used and only sd1.5 is employed, then the generated result is meaningless.

感谢您参与 X2Paddle 社区！ 问题模版为了 X2Paddle 能更好的迭代，例如新功能发布、 RoadMaps 和错误跟踪. :smile_cat: ## 问题描述 将paddleocr转为onnx后转换为fp16，再通过x2paddle转换为paddle时出现错误 - 错误信息 - - 错误截图  ## 具体信息 - 转换模型后用处 - [ ] 使用 Paddle 框架/ PaddleInference 推理预测...