micronet
micronet copied to clipboard
liyunsheng13
Thanks for your great work, but I have trained the `train_micronet_m0_4gpu.sh` script, but got best Acc@1 45.86 at epoch 596, lower than 46.6 reported in your repo with pytorch 1.7.1...
UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor....
Thanks for your gorgeous work, but can you release the code & pretrained models of object detection task
 When I see the code, I can't figure the fule of parameters, Can you explain??
hi， thanks so much for your great work. we have some questions about the MicroNet config for Human Pose Estimation task too. so we appreciate it if you could share...
Hello, I have a question I would like to ask: If the MicroNet network is used for target detection, then as the backbone network, how to modify its output? That...
Hi, thanks for your great work! I am attempting to make this structure work on the pose estimation task. However, I found the modification in your paper which makes me...
I am doing related work based on paddleOCR. I replaced the backbone of the CRNN network structure from mobilenet_v3 to micronet. I train on a single machine with 4 cards,...
My loss down to 0.75 and its hard to converge（150epochs）. I use the M3 model, how can i fix the issue? My data is good and i had done some...
The model you used in the main program is resnet18. When I changed the model to micronet, the following error occurred:' NoneType' object is not callable. Please answer the following...
