Help Needed: Issue Running DeepForest Model for Tree Species Classification

[Abhijitop25]

[
I am trying to install and use DeepForest deep learning model for classifying Indian tree species.
I am reaching out to seek assistance with an issue I am currently facing during the installation and usage of the model. I have followed the provided instructions, but I encountered an error that I am unable to debug. I believe providing with more details, including the error message, the multi_csv.csv file, and a sample image (tr.jpg), will help in diagnosing the problem.

Here is a brief description of the issue:

Error Message:

INFO:pytorch_lightning.callbacks.model_summary:
| Name | Type | Params

0 | model | RetinaNet | 32.2 M
1 | iou_metric | IntersectionOverUnion | 0
2 | mAP_metric | MeanAveragePrecision | 0

31.9 M Trainable params
222 K Non-trainable params
32.2 M Total params
128.675 Total estimated model params size (MB)
/usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/connectors/data_connector.py:441: The 'train_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the num_workers argumenttonum_workers=1in theDataLoaderto improve performance. /usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/connectors/data_connector.py:441: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of thenum_workers argument to num_workers=1 in the DataLoader to improve performance.
Epoch 0: 0%
0/1 [00:00<?, ?it/s]

AttributeError Traceback (most recent call last)
in <cell line: 1>()
----> 1 m.trainer.fit(m)
2 assert m.num_classes == 2

16 frames
/usr/local/lib/python3.10/dist-packages/torch/_utils.py in reraise(self)
692 # instantiate since we don't know how to
693 raise RuntimeError(msg) from None
--> 694 raise exception
695
696

AttributeError: Caught AttributeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.10/dist-packages/deepforest/dataset.py", line 106, in getitem
targets["labels"] = image_annotations.label.apply(
File "/usr/local/lib/python3.10/dist-packages/pandas/core/generic.py", line 5902, in getattr
return object.getattribute(self, name)
AttributeError: 'DataFrame' object has no attribute 'label'
Files Attached:

multi_csv.csv
tr.jpg
Screenshot of the Error:

multi_csv.csv](https://github.com/weecology/DeepForest/files/13688630/multi_csv.csv)

[ethanwhite]

Hi @Abhijitop25 - thanks for the issue. Let's do 2 things to help figure out what the issue is.

1. Can you install the newest development version of the package? If you have git installed on your machine you can do this using:

pip install git+https://[email protected]/weecology/deepforest.git

2. Once you've done that can you run the multi-species example from the docs and share the output?

[ethanwhite]

@Abhijitop25 - we have now released the fixed version so you can just update to the newest version using pip install deepforest --upgrade