Comments (8)
Hi, the provided GT depths, intrinsics, RGB images can satisfy the fine-tuning. You can use 8*4090 for fine-tuning, but the more gpus faster training.
from metric3d.
So, I can follow the same steps as shown in training's readme to fine tune the model, i.e. setting up the dataset as dict and run the training script with parameter "--load-from" set to the path of the pretrained model. Are there additional steps ?
Considering I have a dataset similar to Kitti, what is the approximate number of training data required to fine tune ?
And, by " 8*4090 ", do you mean 8 x rtx 4090 gpus ?
from metric3d.
What is "depth scale" in the json labels ?
from metric3d.
8*4090 is enough for finetuning.
'depth scale' in JSON is used to recover real metric. For example, kitti dataset save the depth map in a 16-bit png file and they scale the real depth with 256 to perserve the numerical precision. Thus in our json, we create this to scale the loaded depth file to recover the metric.
from metric3d.
Hey @testingshanu , may I ask how your configuration file of your custom dataset looks like? I'm stuck in a similar situation
from metric3d.
Hey @testingshanu , may I ask how your configuration file of your custom dataset looks like? I'm stuck in a similar situation
Not yet. If you are able run it successfully, please let me know the config and depth scale that you used.
from metric3d.
Hey @testingshanu , may I ask how your configuration file of your custom dataset looks like? I'm stuck in a similar situation
Not yet. If you are able run it successfully, please let me know the config and depth scale that you used.
Hi, I got it to work. I used the depth scale same as kitti (seen in config and in issue below). Before training I saved my data the same way as kitti does:
def save_as_uint16(depth, filename):
"""
depth is a 2D numpy array containing metric depth as float in meter
"""
# Handle invalid values
depth[np.isnan(depth) | np.isinf(depth)] = 0
# Convert depth to 16-bit unsigned integer format
depth_uint16 = (depth * 256.).astype(np.uint16)
# Save depth as PNG
Image.fromarray(depth_uint16).save(filename)
here is more info and the config also: #105
from metric3d.
Hey @testingshanu , may I ask how your configuration file of your custom dataset looks like? I'm stuck in a similar situation
Not yet. If you are able run it successfully, please let me know the config and depth scale that you used.
Hi, I got it to work. I used the depth scale same as kitti (seen in config and in issue below). Before training I saved my data the same way as kitti does:
def save_as_uint16(depth, filename): """ depth is a 2D numpy array containing metric depth as float in meter """ # Handle invalid values depth[np.isnan(depth) | np.isinf(depth)] = 0 # Convert depth to 16-bit unsigned integer format depth_uint16 = (depth * 256.).astype(np.uint16) # Save depth as PNG Image.fromarray(depth_uint16).save(filename)
here is more info and the config also: #105
Did you also manage to fine tune both kitti and your own dataset ? And did it perform well on your data ?
from metric3d.
Related Issues (20)
- Problem executing onnx/metric3d_onnx_export.py HOT 1
- # Problems in saving the entire model and executing onnx HOT 4
- Normal.npy and Pointcloud shapes doesn't match. HOT 2
- estimate on customized dataset. HOT 1
- Running on lower resolution images. HOT 2
- disparity or depth?
- How do I test for single random test image? HOT 1
- about output ply HOT 1
- nothing
- Ground Truth Depth Image not loading correctly in fine-tuning HOT 1
- Release Request for Preprocess Code for Hypersim Dataset
- issue when runnig test_vit.sh
- About Finetune on Custom Dataset HOT 1
- as for benchmark ,metric3dV2 is the best, but after testing on custom data, depth_anything has a better predicted depth map in most case
- Why do you scale the label when resizing the image? HOT 5
- canonical transform with onnx model HOT 1
- How to achieve corresponding 2D points for each 3D points? HOT 1
- Expected onnx model input mismatch with name in test_onnx.py
- Are the VIT checkpoints on Huggingface the finetuned ones on NYU?
- Infinite Depth
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.