SparseR-CNN

SparseR-CNN copied to clipboard

"Dataset 'CrowdHuman_train' is not registered

3

Can't train on CrowdHuman dataset? Is CrowdHuman still not available on detectron 2 ...? 

Aliweka2020

how to do Grid and Rondom proposal boxes initialization?

5

Thanks for your code. Can you provide the code of Grid and Random initialization method? For example, the specific mean and std paramter of the Gaussian distribution. Thank you very...

liz6688

When I use my own dataset(only 1 class) to evaluation, I got the following error. I'd appreciate it if you could guide me. Traceback (most recent call last): File "G:/SparseR-CNN-main/projects/SparseRCNN/train_net.py",...

YipChakwai

AssertionError: Attribute 'thing_classes' in the metadata of 'coco_2017_train' cannot be set to a different value!

2

[01/28 02:49:28 d2.data.datasets.coco]: Loading datasets/coco/annotations/instances_train2017.json takes 4.76 seconds. Traceback (most recent call last): File "projects/SparseRCNN/train_net.py", line 159, in args=(args,), File "/home/wyw/SparseR-CNN/detectron2/engine/launch.py", line 62, in launch main_func(*args) File "projects/SparseRCNN/train_net.py", line 145,...

Aruen24

the learning rate adjustment when training with one gpu or two gpus

5

Thanks for your code. When I training this code with two GPUs (Tesla P4), changing image_per_batch 4 by running: python projects/SparseRCNN/train_net.py \ --config-file project/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml \ --num-gpus 2 SOLVER.IMS_PER_BATCH 4 **when...

Young0111

Hi,Have you verified the model to ONNX, i meet some bugs to onnx.

2

csliuchang

refactoring code with var unpack

1

refactoring code with var unpack which is more pythonic, concise, readable and efficient; how do think this change which has practical value？ Thanks for your contribution! If you're sending a...

idiomaticrefactoring

我把从coco数据集换成了自己的数据集，但是出现了错误，我应该修改你的代码中的哪几个部分的代码

5

我把从coco数据集换成了自己的数据集，但是出现了错误，我应该修改你的代码中的哪几个部分的代码。 Traceback (most recent call last): File "projects/SparseRCNN/train_net.py", line 159, in args=(args,), File "/home/libing/anaconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/launch.py", line 62, in launch main_func(*args) File "projects/SparseRCNN/train_net.py", line 145, in main trainer = Trainer(cfg) File "/home/libing/anaconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/defaults.py",...

libingDY

'assert (boxes1[:, 2:] >= boxes1[:, :2]).all()' happened when training

4

Thanks for your great work!! When I applied AMP training on detectron2, I found some issues with boxes in the training. ## Changed The difference from the original code is...

Swall0w

How can I use a custom dataset?

2

I want to use a custom dataset other than the coco dataset. How do I change the path?

JEO-96