xiaoxiongli issues

Results 29 issues of


                                            xiaoxiongli

the Small Object detection issue

Dear All, When i training my own dataset(229 category logo, totally 3w+ images) using PVANet, i got mAP = 0.9672, **indeed it is very high. PVANet is indeed so good**,...

I found a bug(it seems) about the image scale rate~

Dear sanghoon: ^_^ @sanghoon I found a bug(i am not sure) list below: in file test.py: im_scale_factors.append(np.array([im_scale_x, im_scale_y, im_scale_x, im_scale_y])) blobs['im_info'] = np.array( [np.hstack((im_blob.shape[2], im_blob.shape[3], im_scales[0]))], dtype=np.float32) which means that...

Do you have a x2 pre-trained model?

你好：请问哪里有scale=2的训练模型？你的 xiaoxiongli

why current_shapes[idx] = bboxes_[i].ReProject(bboxes_[k].Project(gt_shapes_[k])) ?

Dear luoyetx, i am reading your code, and i find that in the trian.cpp, line 180, i can not understand why we do like this? one face's initial shape is...

in lepton, which algorithm to implememnt the idct function?

Hi @danielrh , As you know, there are lots of fast method to implement DCT/IDCT, in lepton, it seems also use fast implement about it. I wannat to know that...

compile error in api_examples/wand.c

### ImageMagick version 7.1.0-27 ### Operating system Linux ### Operating system, version and so on ubuntu-16.04 ### Description when I run below command on linux: `gcc -I`pwd` -LMagickWand/.libs -LMagickCore/.libs -lMagickWand-7.Q16...

训练ESRGAN scale=2的模型报错

你好，训练ESRGAN scale=2的模型报错，报错信息如下： **/data1/lishaoxiong/sr/ESRGAN/BasicSR/basicsr/losses/losses.py:16: UserWarning: Using a target size (torch.Size([2, 3, 128, 128])) that is different to the input size (torch.Size([2, 3, 256, 256])). This will likely lead to incorrect...

xiaoxiongli