Audrey528

@Sammytop123 Are some paremeters, like CONF_THRESH, IOU_THRESHOLD, the same when you get prediction boxes?

@AllentDan Thanks for your reply. as shown below, the test pipeline of model_cfg is set. And I change (1333, 800) to (1344,800), but the error is the same as before....

I set `keep_ratio=False` in model_cfg, but the error still exists

@pprp I don't alter which files to change my own classes, I need some help. Thanks.

@pprp I wanna train voc format dataset using mmdet， I change two places in cwd_cls_head_gfl_r101_fpn_gfl_r50_fpn_1x_coco.py.   I have some questions. 1. I have two classes, which file can I...

@pprp I have solved 1 and 3.

I use cwd distillation method provided by you guys to compress model. I use same datasets in distillation as training process. I have three questions. 1. [email protected] of teacher model...

OK! I have two questions. One is can mmrazor call directly all modules of mmdetection? The other is can I use distilling provided by mmrazor if I added other module...

@pprp @pppppM Thanks for your answers!Just like the following picture says, if I run 'pip install -v -e .', offical mmdet will be installed. I wanna know how can I...

@J-shang I use nni to pruning a model by trained mmdetection and mmrazor. My code is ``` config_list = [{ 'sparsity_per_layer': 0.5, 'op_types': ['Conv2d'], }] pruner = L1NormPruner(model, config_list) #...