xielixun comments

Repositories
Issues
Comments

Results 3 comments of


                                            xielixun

Error with yolo-v3(416*416)

> Did you test the project with yolo-v3(416*416)? > > $ python3 trt_yolo3_module_1batch.py > Reading engine from file yolov3-608.trt > Traceback (most recent call last): > File "trt_yolo3_module_1batch.py", line 214,...

The loss value didn't drop when it came down to about 7.X?

I have the same question, and I search some solving method , I found the batch_norm_param use_global_stats must be false, after I add the param , my trainning loss is...

why it is much slower when i training mobilenetv2-ssdlite than v1,it all most cost one day can only iterate 5000 times,but according to the paper it should much faster,isn't it?

> same issue, has this problem been solved ? Do you use src/cudnn_conv_layer.cpp and src/cudnn_conv_layer.cu , and compile SSD, which is chuanqi305 support in the rep src file. If use...