-
Hey there Linamo1214,
First of all, great job with the trt. I have one question though. I have proceeded with the conversion like this.
On my laptop, running Ubuntu 22.04, without any NVIDIA GPU…
-
### What is the feature?
Hello, when I run "tests\test_evaluation\test_functional\test_kitti_eval.py" to test that the test_do_eval() evaluation function is correct, the results are normal;
Howeve…
-
Hi there, exciting work and thanks for your code.
I just have a quick question about how to calculate the volume IoU given two meshes. Is there any elegant way to do that?
-
File "D:\code\MonoDETR\lib\models\monodetr\matcher.py", line 83, in forward
cost_giou = -generalized_box_iou(box_cxcylrtb_to_xyxy(out_bbox), box_cxcylrtb_to_xyxy(tgt_bbox))
File "D:\code\Mon…
-
Saw this degraded performance on KVM in CLH compare to QEMU. Ran the test on Same Host (Dell Precision 3630 Desktop, Baremetl scenerio, CPU:Intel(R) Core(TM) i7-9700K CPU @ 3.60GHz 8 cores) Mem: 64GB
…
-
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 …
-
According to the [RCTW-17 paper on arXiv](https://arxiv.org/pdf/1708.09585.pdf), it says,
> A detection is matched to a groundtruth and marked as true
> positive if 1) IoU is over 0.5 and 2) the …
-
*I trained using the McGill hockey dataset.
*I created the json file properly, and it is as follows.
(my ds)
{"images": [
{"file_name": "car_bos_2019_001/img1/000001.jpg", "id": 1, "frame_id"…
-
I'm doing segmentation on images with 3 classes, instead of 2. So I changed
`dice_loss = sm.losses.DiceLoss(class_weights=np.array([1, 2, 0.5])) `
to
`dice_loss = sm.losses.DiceLoss(class_wei…
-
Hi,
I'm trying to train darknet using satellite images. I'm using a Vedai data set, see here: https://downloads.greyc.fr/vedai/ which comes with pre-annotated images.
When training, using comman…