iamweiweishi

Hi, I am tring to get the outputs of the albert model given an input, ` def load_pretrained_albert(): albert_dir = "albert_base" model_params = bert.params_from_pretrained_ckpt(albert_dir) l_bert = bert.BertModelLayer.from_params(model_params, name="albert") # use...

请问下有什么阈值可以调节么

1

我跟踪时 丢ID还是比较严重的，有什么阈值可以调么？ 非常感谢

Could mmtracking support anchor-free detectors for VID

2

**Currently, the SELSA use the faster RCNN as the main structure for video detetion. Anchor free detectors, like YOLOX, are showing powerful performance. I wonder could I use YOLOX as...

Inconsistent infer results for stream-transducer and stream-transducer-tflite models

9

After getting help from [this](https://github.com/TensorSpeech/TensorFlowASR/issues/168), I successfully trained a stream-ransducer model and converted the model to tflite. I tested the trained model with "test_subword_streaming_transducer.py" first, the predicted result seems to...

Hi, Could the provided pretrained model be run on CPU? Thank you.

Android Support？

2

你好，请教下本工程可能转到安卓使用么

Thank you for your geat work. I trained a TCResNet8 model and then converted to tflite-model successfully. But I do not know how to use the tflite model when I...

Will the CONV operation be released in future?

3

Thank you for your great contribution. I noticed that the dense layer could be incorporated in VGG successfully, but I did not found the implementation of CONV layer, I would...

I followed your instructions and the 'make' is correctly done. But when I run 'python test_gemm_op.py', I got the errors, `/usr/local/lib/python3.6/dist-packages/numpy/lib/type_check.py:546: DeprecationWarning: np.asscalar(a) is deprecated since NumPy v1.16, use a.item()...

ImportError: No module named voice_recognize.extract_feature.feature_compute

1

Hi, there The file is missed. Could you pls help with this? Many thanks.