Comments (3)
Hello, thank you for your kind words!
But I have a question while using it. In the code, when normalizing the image, is the order of
mean = torch.tensor([123.675, 116.28, 103.53])
in RGB or BGR?I found that the line of code
rgb_origin = cv2.imread(an['rgb'])[:, :, ::-1].copy().astype(np.float32)
inMetric3D/mono/utils/do_test.py
Line 244 in 377e6c6
has already converted the default BGR format, which is read by cv2.imread(), to RGB when reading the image.
Then, in this line of codergb = cv2.cvtColor(rgb, cv2.COLOR_BGR2RGB)
in https://github.com/YvanYin/Metric3D/blob/377e6c6642d0aca7aaa5a19e58fdcf5d0fd3d910/mono/utils/do_test.py#L189C5-L189C47, there is another conversion, which means the image is converted back to the BGR order. However, your comment says "BGR->RGB", so I would like to know whether the mean used for normalization is in RGB order or BGR order?If I understand correctly, this normalization method is used to match the pre-trained ConvNext. However, it seems there is ambiguity here. Did you normalize the data in the training process in the same way, following the BGR order?
Thanks for pointing out this issue. We will fix it now.
from metric3d.
Thanks for your reply!
from metric3d.
Hi, I wanna know why this line still exits: rgb_origin = cv2.imread(an['rgb'])[:, :, ::-1].copy()
I wanna know we should use RGB order or BGR order for the input of the model??? @JUGGHM
from metric3d.
Related Issues (20)
- Pixel represented focal length or real world scale focal length(mm) HOT 4
- Some problems in Training HOT 3
- Supporting old GPUs? HOT 3
- metric_scale in nyu.py HOT 1
- Speed Up Inference HOT 2
- NYU dataset and json HOT 1
- Inference Speed data
- normals not normal HOT 2
- Unable to adjust scale of depth correctly in the wild-mode HOT 1
- How to convert the DINO2reg-ViT model to an ONNX model HOT 2
- torch.hub.load error HOT 4
- Failed to find function: mono.model.backbones.convnext_large HOT 1
- Fine tune on custom dataset HOT 8
- Sparse GT depth from LiDAR for supervision? HOT 1
- Question regarding losses HOT 1
- Depth scale vs Metric scale HOT 6
- What does the pkl file contain in training with Matterport3D? HOT 1
- generate only a depth matrix without generating a 3D point cloud HOT 2
- Is there any reference code to generate kitti dataset annotation?
- Camera parameters of taskonomy HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from metric3d.