Jungmin_ML_DL_CV_LLM issues

Results 16 issues of


                                            Jungmin_ML_DL_CV_LLM

AttributeError: module 'ppdet.data.source' has no attribute 'test'

### 问题确认 Search before asking - [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有发现相似的bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/issues) and found no similar bug report. ### Bug组件 Bug Component Training ### Bug描述 Describe the Bug ====================================================================== ERROR:...

bug

OSError: (External) CUDA error(719), unspecified launch failure.

bug

pretrained weight model

Hi, I can't download the pretrained weight model in baidu. could you send me the model by email? [email protected]

how come can use tfrecord by face-mesh-generator?

Hi, I finished wflw dataset using face-mesh-generator in colab environment. I just got tfrecord and what is that? How can I use it for training on hrnet? do I have...

increasing accuracy if using only eye eyebrow nose landmark

Hi, thanks for great works. I have some question, if only eye, eyebrow, nose part for training, accuracy is increasing? my concern is large pose and occlusion image make some...

tf2 model or tflite

Hi, do u have tf model or tflite model?

where is encoding based model?

Hi, I am not sure this code for optimization based model is good... Because it is not similar to inverted face img to source img. And I am wondering if...

two question invertor and FFHQ training

Hi, thanks for nice works. I am really interesting your works. Did you have FFHQmask pretrained model instead of CelebA? If you had, plz update it. thanks. For invertor, you...

where is loss function line in MLP for training? is it using?

Is it possible to posed image to frontal image like inverse method in figures?

for example, source is pose image and target is frontal image