Fateeeeee

Pre-training weight

5

Hello, where are the pre-training weights of YOLOv4-CSP ending in pt? I only saw the ones ending in .weights.

官方用例报错，LogWriter对象没有mode属性

4

logdir = "/workspace" logger = LogWriter(logdir, sync_cycle=100) # mark the components with 'train' label. with logger.mode("train"): # create a scalar component called 'scalars/' scalar_keras_train_loss = logger.scalar( "scalars/scalar_keras_train_loss") image_input = logger.image("images/input",...

why the gpu memory is rising when training?

1

Finally,the memory explodes

Import Error

3

from . import ddf_mul_ext, ddf_mul_faster_ext, ddf_add_ext, ddf_add_faster_ext ImportError: /home/user/Desktop/xx/DDF/ddf/ddf_mul_ext.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZNSt15__exception_ptr13exception_ptr9_M_addrefEv

Hello, this is solid work. Can you please provide the code related to the anchor constraint before Kmeans? I can't find it in the project.

Which file is the supervision loss of CAM in?

1

Thank you for your great work！ I am not very familiar with the structure of mmdet, which file is the supervision loss of CAM?