Yuntao Chen
Yuntao Chen
You can free it up freely. Just batches of data. On Thu, Jan 2, 2020 at 2:28 PM zhangxue123 wrote: > I used 'free -g' notice buff/cache progressively increase during...
Bug confirmed. It seems we forget to add graph optimization for rpn_test. https://github.com/TuSimple/simpledet/blob/78467b7233d33d09b692ee4ca5fb3cbe46b85ee5/mask_test.py#L95-L98
Which pip wheel did you use? On Mon, Feb 10, 2020 at 4:56 PM nihuizhidao wrote: > After installation following introductions in README.md，when I run > > python detection_infer_speed.py --config...
You may need a label map json file to map your classname to train id. https://github.com/TuSimple/simpledet/blob/f67fca08b33d957b43eb1db5e3745a3a9e3803b5/utils/create_voc_roidb.py#L52
Just plain kv pairs as { "category_name": train_id } On Tue, Dec 24, 2019 at 9:23 AM MTfast wrote: > What is the format of this json file? > >...
you can write it with any text editor On Wed, Jun 10, 2020 at 7:03 PM dongjun wrote: > Hi, how can I make that voc_label_map.json? > could you know...
The proposal operator has some problems when handling invalid input, which leads to a segment fault when the input contains NaN. This means your Cascade R-CNN heads or the RPN...
Do you want to test the model with 2 GPUs?
The batched test can not be achieved since during the test we do not pad the image. So each image has its unique shape and the 1 image per GPU...