yahuuu

How to modify the convolution property to same.

1

I converted onnx to h5, but found that the padding property in the convolution is valid, how to modify the property to same. Whether this property affects the speed when...

WinMLRunner.exe. Evaluating ..[FAILED]

4

I convert the pt model to the onnx model and verify that the onnx model has good output accuracy. But my onnx model cannot evaluateing with GPU. I only saved...

Integer tflite model slow than float32 model

11

### 1. System information - quantized integer tflite model in Window10(without Nvidia GPU) - TensorFlow installation method pip installed tensorflow-gpu-2.2.2 and tensorflow-2.2.2. - try to run quantized model in mobile...

训练时报错

2

当我运行ValueError: dimension mismatch.py尝试训练时遇到 Traceback (most recent call last): File "C:/work/py/78stars_SpamMessage-master/token_and_save_to_file.py", line 38, in data = Pool().map(jieba.lcut, data) File "C:\Users\yah\Anaconda3\lib\multiprocessing\pool.py", line 268, in map return self._map_async(func, iterable, mapstar, chunksize).get() File "C:\Users\yah\Anaconda3\lib\multiprocessing\pool.py",...

bayes_evaluator.py中的Evaluator类似乎有错误， 在self.trainer.train_classifier()训练时是训练调用类的self.clf = GaussianNB()该模型保存到'model/bayes_estimator.pkl'中， 在预测时候用的是模型'model/Terminal_estimator.pkl'。 简单说就是训练保存的模型和预测用的模型不同，是不是逻辑错误。请楼主看下。