superchenyan
superchenyan
Maybe there are some problems in the test code. The author's model is ok. I train the model based on the author provided dataset, I find it randomly print Check...
@nqanh I suspect there is something wrong with the test code. I use the data you provided for training. When I test different iterations of the model, some models report...
@nqanh @ambl2357 Do you solved this problem? I test the model of 60K iterations, it still report "error == cudaSuccess (2 vs. 0) out of memory", I wonder why ?...
@nqanh I'v fine-tuned imagenet pre-trained model with my custom dataset， and I changed the name of bbox_pred layer with 'bbox_pred_face' The problem comes from the snapshot wrapper in train.py. This...
This reply is for original "AssertionError: Selective search data not found". I encountered this problem and found a way to solve it. The main cause of this error is the...
多边形你取最大外接矩形作为检测框，19类分割，你只需把分割的label在label_map_seg里对应起来就行了
是的，你只需要替换为你的label名字就行，我没有用cityscape数据训练，我用我自己的一些数据做的，
> I have modified the image_data layer to support read images and annotation boxes. If you want the file, you could give me your Email. Ths ! my email is...
> > I have modified the image_data layer to support read images and annotation boxes. If you want the file, you could give me your Email. > > Wow,thanks, that's...
这是因为验证集的名字和lfw的格式不一致，要么修改dataloader那块： path0 = os.path.join(lfw_dir, pair[0], pair[0] + '_' + '%04d' % int(pair[1])+'.'+file_ext) path1 = os.path.join(lfw_dir, pair[0], pair[0] + '_' + '%04d' % int(pair[2])+'.'+file_ext) 这块图像路径需要修改。 要么把图像格式按lfw重新命名。