ardeal

According to my knowledge, even if we have much less training samples, the algorithms can be trained correctly. The only problem should be that the classification or regression accuracy is...

I should prepare training images and parameters to train a new model, right? According to your experiments, what image datasets are used to train the model? Did you get the...

Could you please share the data format in the following files? how is the data organized in ../data/face.txt and others? ``` "data": { "use_hard": false, "face": "../data/face.txt", "background": ["../data/hd.txt", "../data/background1.txt",...

Hi, in Cart::SplitNodeWithRegression function of cart.cpp file: ``` int threshold_ = pos_feature_sorted(0, int(pos_n*rng.uniform(0.1, 0.9))); ``` You got the split threshold by a random way, is this reasonable? or, did you...

I am trying to train the algorithm with 76 pos samples and 1671 neg samples. I merely want to verify whether the code works correctly. but I got the following...

@MohamedA95 , The code could be run. if the `weight_quant_type` syntax is wrong, it should report error instead of warning. You could find the same example syntax in `brevitas` github...

@MohamedA95 , Thank you! To use `torch.nn.Softmax()` in code is not difficult, my question is: the output of the upper layer(`qnn.QuantLinear`) is quantized data, could it be passed to `torch.nn.Softmax()`...

@NaleRaphael , You argument `suggest_lr` works. Thanks!

@abhiksark @zhongxing9006 @onefish51 @H-YunHui @yyx1107 have you solved the problem? Please see my issue #504 I am experiencing the same problem. I just clone the code and prepare COCO. nothing...

This issue is quite weird: if I change my python to 3.6, the issue on VS2015 is: LINK : fatal error LNK1104: cannot open file 'python35.lib' however, If I change...