xuchen-dev

question about valid

17

i think train the model successful，i dont change anything in the code the result looks good  it is about 10 epoch result but the a1 a2 a3 rmse and...

i think may be use -2 -1 0 1 2 would be better so i change the code  but the resultresult is not so good 

pytorch version

5

hi i want to build a pytorch version base on a pytorch version mask-rcnn like this https://github.com/facebookresearch/maskrcnn-benchmark/tree/main/maskrcnn_benchmark could you give me some advice ，i will be very grateful

for eval

3

very hopeful for your help： i use your fastercnn.py as a moudle in my model , when train it is very good the result is good too but when eval...

cmake .. -DTENSORRT_ROOT=/usr/src/tensorrt/bin/trtexec && make -j -- The CXX compiler identification is GNU 9.4.0 -- The C compiler identification is GNU 9.4.0 -- Check for working CXX compiler: /usr/bin/c++ --...

**Describe the bug** onnx_model, check = simplify(onnx_model, skipped_optimizers=["FuseConsecutiveSqueezes"]) when i use this skipped_optimizers , two squeeze still be fused

Train_log

1

Hello, I would like to use your code to quantify sd-v15. Can you provide me with your training log ， I am trying to train models that not with TALSQ，but...

Always stuck here

1

 Did I make a mistake in any step， it always stuck here