-
Hi,
I trained different default model configurations (mask_rcnn, cascade) with different backbones (swin, r50, x101) for a custom COCO formatted dataset. The dataset contains only one class with u…
-
My server does not have 8 GPUs. When I use 4 GPUs for training (without any modification to the network), I just change num-gpus to 4. After training, the segmentation accuracy is always 0.00. Do you …
-
unexpected key in source state_dict: fc.weight, fc.bias
E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\mmdet\datasets\custom.py:154: UserWarning: CustomDataset does not support filtering…
-
In my parameter Settings, I annotated all the MASK part of HTC, at this time I saw that the program can be trained, and the RPN part used HTC module. Is this using the HTC module?
-
Hi,
I'm trying to reproduce Your results in instance segmentation, using the scripts that you delivered (train_maskyolo_step1.sh and 2). I did everything according to the instruction. The scripts wor…
-
Hi,
Is there anyone who would like to share the training file? I tried to set up by myself but failed.
```
model = dict(
type='MGAN',
pretrained='modelzoo://vgg16',
backbone=d…
-
ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 88 from C header, got 80 from PyObject
error after try to run an execution test from https://github.com/carlos…
-
您好！我使用您的框架mmrotate0.2.0训练测试HRSC2016数据集的性能，分别使用了ReDet和Roi trans等模型，发现测试集上的性能与使用ReDet论文作者发布的代码 差距很大，特别是AP75和mAP。而配置都是一样的，基本没改过。
backend_args = None
data_root = '/data/luoyq/data/toutu/v3'
dataset_type = 'VOCDataset'
default_hooks = dict(
checkpoint=dict(rule='gre…
-
## Description
I tried to convert `QDQ DepthwizeConv > BatchNorm > Swish(Sigmoid, Mul)` model by using trtexec, but it fails with the error below.
> [E] Error[10]: [optimizer.cpp::computeCosts::…