liangzimei
liangzimei
i can't find the log in /tmp and /fastrcnn, how can I get the log file ,thanks....
when i change softmaxwithloss to focal-loss, in the beginning of training, the loss becomes 87.3365. When using softmaxwithloss, there is no such a problem. Is the code still under the...
in my person detection task, when i use softnms in testing, the ap drops a little. in default, is(should) the softnms used in training.? thank you....
hi, i have already achieve ~94% with 4000 labels on cifar10. But for my own three classification task, i have 160k labelled data and unlabelled data. i can not get...
hi , firstly thanks for your great work for ssl. But when i refer many resnext nets of pytorch, there are no ShiftConvDownsample layer? what is the function of it?...
请问中文OCR使用 attention 效果好还是ctc好呢
Hi, it‘’s my first time to try domain adaptation. Here is my scenario: i am doing a image classification task, there are already 100k training data with labels (called A),...
when i run this demo, there is a error Check failed: error == cudaSuccess (2 vs. 0) out of memory. my gpu is k80, i think the memory is enough...
Very nice work, can this method combine with CTC in 1D case to improve performace further? does it conflict with CTC when training?
hello, i run the imagenet classification demo, i find it is slower when setting quantize=ture, is it normal? [using quantization](https://github.com/tidsp/caffe-jacinto-models/blob/caffe-0.16/trained/image_classification/imagenet_jacintonet11v2/test_quantize/run.sh) [not using quantization](https://github.com/tidsp/caffe-jacinto-models/blob/caffe-0.16/trained/image_classification/imagenet_jacintonet11v2/test/run.sh)