DeepForest icon indicating copy to clipboard operation
DeepForest copied to clipboard

Python Package for Airborne RGB machine learning

Results 194 DeepForest issues
Sort by recently updated
recently updated
newest added

RuntimeError: Error(s) in loading state_dict for RetinaNet: size mismatch for head.classification_head.cls_logits.weight: copying a param with shape torch.Size([9, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([18, 256,...

Excuse me I am quite a beginner and I apologies if this is a trivial question. I would like to use DeepForest on large area about 50000 square km. Does...

**Describe the bug** ``` Traceback (most recent call last): File "C:\Users\Thomas\anaconda3\envs\deepf\lib\site-packages\spyder_kernels\py3compat.py", line 356, in compat_exec exec(code, globals, locals) File "c:\gisdb\python\pydeepf.py", line 10, in from deepforest import main ImportError: cannot import...

Hello, I am trying to train with RGB images of different size. However, since epoch 0 the loss function is not being computed. I only have a NaN from the...

I really like Deepforest. It works great and I was wondering if it can run on Torchserve. It would be great if I could use it together with Torchserve. But...

enhancement

**Describe the bug** In [main.py](https://github.com/weecology/DeepForest/blob/02aac1fd8105f18e63c321be170c2c55d82a51c6/deepforest/main.py#L127), the `enable_checkpointing=False` is hard coded. When I pass a lightning ModelCheckpoint to `create_trainer()` then it throws the error: `Trainer was configured with "enable_checkpointing=False" but found...

Hi there, I'm revisiting Deepforest again after not using it for 18months - things have changed a lot! This question was previously an issue about getting the GPU working, but...

**Describe the bug** Trying to run the colab linked to in README errors with: `ImportError: cannot import name 'functional' from 'albumentations'` **To Reproduce** 1. Open https://colab.research.google.com/drive/1gKUiocwfCvcvVfiKzAaf6voiUVL2KK_r?usp=sharing in your browser 1....

**Describe the bug** When using the `evaluate.evaluate` function on the prediction made by `predict.predict_image`, an error is shown ``` File "reproject.py", line 39, in results = model.evaluate(csv_file, root_dir, iou_threshold=0.4, savedir=None)...