-
I noticed the article's 3D backbone is pretrained model like resnet, I wonder if the model is pretrained independently on other datasets like kinetics400 and the used in YOWOv3 directly? I mean, how t…
-
Hi,
Thanks for your impressive work! I want to know if, you train the denoiser with Pointnet++ from scratch? Have you ever try to train denoiser with pretrained weights of PointNet++, or any other …
-
Seems like pertained ms1mv3 arcface models cant be pretrained with a smaller custom dataset. Is that correct.
def _iresnet(arch, block, layers, pretrained, progress, **kwargs):
model = IResNet…
-
I have fine-tuned and quantized faster_rcnn model for the use but when I load it...
RuntimeError Traceback (most recent call last)
[](https://ef4m8e4i83j-496ff2e9c6d22…
-
class ImageEncoder(nn.Module):
def __init__(self, sam_model: SAM2Base) -> None:
super().__init__()
self.model = sam_model
self.no_mem_embed = sam_model.no_mem_embed #[1…
eakey updated
2 weeks ago
-
### Question
我在salience_detr.py中的 `class SalienceDETR(DNDETRDetector):` 类 加入了
`self.Re_Weight = WeightRefactor(sample_num)`,使用resnet50 backbone可以训练,但是swin_l 会报错:
`[2024-11-11 20:07:56 det.models.…
-
报错如下所示。使用的是README中提供的预训练模型Apolloscape/model.ckpt,似乎是模型尺寸不匹配。
```shell
> python3 scripts/benchmark_val.py …
-
**Is your feature request related to a problem? Please describe.**
No, problem, Just an addition of an interesting bacbone to the timm library
**Describe the solution you'd like**
Addition of Uni…
-
from the conversation with @biancazadrozny and Johannes Schmude:
- Enable more complex embedding networks (convolutions; optionally also pixel shuffle)
- Enable more complex heads (convolutions; opti…
-
错误:
Traceback (most recent call last):
File "/root/musc/examples/musc_main_clone.py", line 90, in
model.main()
File "/root/musc/models/musc_clone.py", line 237, in main
self.make_cat…