Sean

> No ETA. Working on mask-rcnn first. Thanks for your remarking work... And I'm interested in Faster R-CNN and cascade_mask_rcnn_r101_fpn_1x too ...... Or any instructions on how to build my...

This is the result txt file. As you can see, ID 142 appear twice in this frame, and the two boxes' center is similar.

142, 1, 39.2249, 12.2663, 0.2982, 0.9574, 0.8843, 1.8107, -3.0537, 0.58 142, 1, 39.4016, 11.4462, 0.1279, 0.8376, 0.7933, 1.5519, -3.0098, 0.78

same question, did you solve it? Thanks

[E] [TRT] (Unnamed Layer* 18) [Convolution]: kernel weights has count 3072 but 1024 was expected My class nums is modified to 1, and when I convert 'wts' to 'engine', this...

> Have you changed the model tpye? s/m/l/x? yes, I've changed it...

> Could you please describe which config you are using? I'm using this one: tridentnet_r101v2c4_c5_multiscale_addminival_3x_fp16.py and it has started training for several hours... Maybe there is something wrong with my...

> Which dataset are you using and what about your hardware? It is my own dataset. Voc style.. But I think maybe some annotations has no objects. Will this cause...

> Could you please locate the input that will trigger this problem?   I add print function in the 'worker'. And I got this KeyError... I'm using 2 1080Ti...

I found that when using only 1 GPU, there is no problem... So I can only use 1 GPU now...