-
Since it seems that the complete training code will never be released, is there anyone who would kindly share their working code?
Thanks in advance
-
my loss curve looks something like this.
model_name: "flux-dev"
data_config:
train_batch_size: 1
num_workers: 4
img_size: 512
img_dir: xxx
report_to: wandb
train_batch_size: 1
out…
-
Hi, I've been trying to train / fine tune the Zoedepth using images that focuses on object in front of a wall, the wall itself is 5 meters depth [as you can see on the distribution graph, the pixel wi…
-
Thanks to the authors for their outstanding contribution. I have successfully reproduced the results of the paper. However, I have encountered new confusion.
At first, I failed to reproduce the res…
-
In our app, we are using only READ_MEDIA_IMAGES permission, we don't use READ_MEDIA_VIDEO permission in our app. But somehow, Play Store shows that our app uses both permissions. So my question is, by…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
I'm using a custom dataset, which is small, 4000 + images, and running train.py after running the dataset_tool.py code which is having problems。
Total 36231618 736 - …
-
Hey. Has anyone tried training with custom dataset?
I manually labeled about 1000 images with lane, disabled crop-preprocess & segmentation loss, modified the max_lanes to 8(num_topk in CollectCLRNet…
-
### Describe the bug
## Bug
I am doing a transfer-learning training using the pre-trained COCO YOLOv8 checkpoint. I create a custom `data.yaml` which passes 7 labels to predict. A `print(model.names)…
-
I am extremely grateful for your work. Now that running and training these codes has resulted in the generation of rendered images, depth maps, normal maps, and point clouds, could you kindly guide me…