Dong

questions about scale variation

1

I'm really interested in your amazing work and I've tried it ,here I would want to ask for your advice: Are there any methods for scale variation? Because I found...

self._normalize() got NAN...

5

### Bug description Sir, when I print upsampled_a in ` upsampled_a = self._normalize(self.hook_a, self.hook_a.ndim - 2)` I got NAN in some value. Is there any bug? I set model to...

create_train.py error

2

find some error here ``` a = 1 - 0.5 * uniform(0, 1) m = gt_image.shape[0] n = gt_image.shape[1] rep_atmosphere = np.tile(np.reshape(A, [1, 1, 3]), [m, n, 1]) ... h5f.create_dataset('atom',data=rep_atmosphere)...

`RuntimeError: expand(torch.cuda.FloatTensor{[1, 3, 512, 512]}, size=[3, 512, 512]): the number of sizes provided (3) must be greater or equal to the number of dimensions in the tensor (4)` change comment...

Hello, I'm a beginner of torch, I read your paper and run your code. During the training part,you used a stage-wise learning in your paper.But in your code, it just...

请问每个蓝色思考题能否给出答案呢？问的都非常好，但是因为自学 ， 有的不懂、不清楚理解的是否正确。非常感谢！

Deployment problem

3

when I follow the deployment steps,error occurs as follow: dong@dong:~/Downloads/caffe-ssd/examples/rbox/deploy/Airplane$ python deploy.py ``` WARNING: Logging before InitGoogleLogging() is written to STDERR W1224 12:42:21.621986 21588 _caffe.cpp:122] DEPRECATION WARNING - deprecated use...

 `CXX tools/upgrade_net_proto_binary.cpp CXX examples/rbox/deploy/librbox.cpp examples/rbox/deploy/librbox.cpp: In function ‘double Overlap(double*, double*)’: examples/rbox/deploy/librbox.cpp:567:7: warning: unused variable ‘i’ [-Wunused-variable] int i; ^ examples/rbox/deploy/librbox.cpp: In function ‘void DecodeAndNMS(double*, double*, int*, double*, int*, double)’:...

大神您好，请问下面几种方法对应的是哪些量化方法，有没有具体的论文，谢谢！ if quantized == 1: modules.add_module('Conv2d', BNFold_QuantizedConv2d_For_FPGA() elif quantized == 2: modules.add_module('Conv2d', TPSQ_BNFold_QuantizedConv2d_For_FPGA()) elif quantized == 3: modules.add_module('Conv2d', BNFold_COSPTQuantizedConv2d_For_FPGA(), 您的readme中quantized 2 对应Dorefa，但在代码中没有调用quantized_dorefa.py, 这个对应是对的吗？ quantized=3 时是哪种量化方法？ FPGA参数是如何使用，起到什么作用呢？ 非常感谢