-
def compute_iou(self,bbox1,bbox2):
# 获取box1的第一个维度
N = bbox1.size(0)
# 获取box2的第一个维度
M = bbox2.size(0)
# Compute left-top coordinate of the intersections
…
-
Dear Alexey @AlexeyAB
Greetings!
We are trying to run training on multi-GPU with 4-K80 cards on Linux machine. We are receiving below error message when we switch the training to multi-gpu afte…
-
Epoch 0
Epoch 1 Step 30 |(30/30)| ETA: 1.48|Total loss:1.88982|Binary loss:1.06663|Instance loss:0.82319|IoU:0.41936
97%|#########6| 29/30 [00:57
-
there is no pretrain weight for GVSR, so I followed your training but I cannot reproduce score.
this is my output after training
CIDEr : 0.44,
{'loss_SRL': tensor(2.4280), 'loss_vb': tensor(4.…
-
-
There is an error in the map part when learning. If you don't give -map , it doesn't sit and it goes well.
darknet.exe detector train data/obj.data cfg/yolov4_tiny.cfg yolov4-tiny.conv.29 -map
…
-
目前是否支持2个3D Oriented Boxes的IOU loss计算？
-
Hi !
A quick question about a loss, I've used quite a few losses and loss mixtures without any problems, but when I use iou loss, I only get empty predictions. My ground truth is a multiclass mask, w…
-
emm, I have question about train cls_loss ,when I train on my own data ,the class loss can't down in 0.999,I check my data, and even change the learnning rate , but is not work, could you give me som…
-
C:\Users\bxf\anaconda3\envs\transt\python.exe C:/PyCharmProjects/TransT-main/ltr/run_training.py
Training: transt transt
WARNING: You are using tensorboardX instead sis you have a too old pytorch …