AutoMM Detection - Fast Finetune on COCO Format Dataset

https://automl-mm-bench.s3.amazonaws.com/object_detection/example_image/pothole144_gt.jpg

Fig. 2 Pothole Dataset

In this section, our goal is to fast finetune and evaluate a pretrained model on Pothole dataset in COCO format. Pothole is a single object, i.e. pothole, detection dataset, containing 665 images with bounding box annotations for the creation of detection models and can work as POC/POV for the maintenance of roads. See AutoMM Detection - Prepare Pascal VOC Dataset for how to prepare Pothole dataset.

To start, let’s import MultiModalPredictor:

from autogluon.multimodal import MultiModalPredictor

The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling transformers.utils.move_cache().
Moving 0 files to the new cache system

0it [00:00, ?it/s]

Make sure mmcv-full and mmdet are installed:

!mim install mmcv-full
!pip install mmdet

Looking in links: https://download.openmmlab.com/mmcv/dist/cu117/torch1.13.0/index.html
Requirement already satisfied: mmcv-full in /home/ci/opt/venv/lib/python3.8/site-packages (1.7.1)
Requirement already satisfied: opencv-python>=3 in /home/ci/opt/venv/lib/python3.8/site-packages (from mmcv-full) (4.7.0.68)
Requirement already satisfied: addict in /home/ci/opt/venv/lib/python3.8/site-packages (from mmcv-full) (2.4.0)
Requirement already satisfied: numpy in /home/ci/opt/venv/lib/python3.8/site-packages (from mmcv-full) (1.23.5)
Requirement already satisfied: packaging in /home/ci/opt/venv/lib/python3.8/site-packages (from mmcv-full) (23.0)
Requirement already satisfied: Pillow in /home/ci/opt/venv/lib/python3.8/site-packages (from mmcv-full) (9.4.0)
Requirement already satisfied: pyyaml in /home/ci/opt/venv/lib/python3.8/site-packages (from mmcv-full) (5.4.1)
Requirement already satisfied: yapf in /home/ci/opt/venv/lib/python3.8/site-packages (from mmcv-full) (0.32.0)
Requirement already satisfied: mmdet in /home/ci/opt/venv/lib/python3.8/site-packages (2.28.1)
Requirement already satisfied: terminaltables in /home/ci/opt/venv/lib/python3.8/site-packages (from mmdet) (3.1.10)
Requirement already satisfied: scipy in /home/ci/opt/venv/lib/python3.8/site-packages (from mmdet) (1.10.0)
Requirement already satisfied: matplotlib in /home/ci/opt/venv/lib/python3.8/site-packages (from mmdet) (3.6.3)
Requirement already satisfied: pycocotools in /home/ci/opt/venv/lib/python3.8/site-packages (from mmdet) (2.0.6)
Requirement already satisfied: six in /home/ci/opt/venv/lib/python3.8/site-packages (from mmdet) (1.16.0)
Requirement already satisfied: numpy in /home/ci/opt/venv/lib/python3.8/site-packages (from mmdet) (1.23.5)
Requirement already satisfied: kiwisolver>=1.0.1 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (1.4.4)
Requirement already satisfied: packaging>=20.0 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (23.0)
Requirement already satisfied: pillow>=6.2.0 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (9.4.0)
Requirement already satisfied: pyparsing>=2.2.1 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (3.0.9)
Requirement already satisfied: cycler>=0.10 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (4.38.0)
Requirement already satisfied: contourpy>=1.0.1 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (1.0.7)
Requirement already satisfied: python-dateutil>=2.7 in /home/ci/opt/venv/lib/python3.8/site-packages (from matplotlib->mmdet) (2.8.2)

And also import some other packages that will be used in this tutorial:

import os
import time

from autogluon.core.utils.loaders import load_zip

We have the sample dataset ready in the cloud. Let’s download it:

zip_file = "https://automl-mm-bench.s3.amazonaws.com/object_detection/dataset/pothole.zip"
download_dir = "./pothole"

load_zip.unzip(zip_file, unzip_dir=download_dir)
data_dir = os.path.join(download_dir, "pothole")
train_path = os.path.join(data_dir, "Annotations", "usersplit_train_cocoformat.json")
val_path = os.path.join(data_dir, "Annotations", "usersplit_val_cocoformat.json")
test_path = os.path.join(data_dir, "Annotations", "usersplit_test_cocoformat.json")

Downloading ./pothole/file.zip from https://automl-mm-bench.s3.amazonaws.com/object_detection/dataset/pothole.zip...

100%|██████████| 351M/351M [00:06<00:00, 50.8MiB/s]

While using COCO format dataset, the input is the json annotation file of the dataset split. In this example, usersplit_train_cocoformat.json is the annotation file of the train split. usersplit_val_cocoformat.json is the annotation file of the validation split. And usersplit_test_cocoformat.json is the annotation file of the test split.

We select the YOLOv3 with MobileNetV2 as backbone, and input resolution is 320x320, pretrained on COCO dataset. With this setting, it is fast to finetune or inference, and easy to deploy. And we use all the GPUs (if any):

checkpoint_name = "yolov3_mobilenetv2_320_300e_coco"
num_gpus = -1  # use all GPUs

We create the MultiModalPredictor with selected checkpoint name and number of GPUs. We need to specify the problem_type to "object_detection", and also provide a sample_data_path for the predictor to infer the catgories of the dataset. Here we provide the train_path, and it also works using any other split of this dataset.

predictor = MultiModalPredictor(
    hyperparameters={
        "model.mmdet_image.checkpoint_name": checkpoint_name,
        "env.num_gpus": num_gpus,
    },
    problem_type="object_detection",
    sample_data_path=train_path,
)

processing yolov3_mobilenetv2_320_300e_coco...

Output()





Successfully downloaded yolov3_mobilenetv2_320_300e_coco_20210719_215349-d18dff72.pth to /home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune
Successfully dumped yolov3_mobilenetv2_320_300e_coco.py to /home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune
processing yolov3_mobilenetv2_320_300e_coco...
yolov3_mobilenetv2_320_300e_coco_20210719_215349-d18dff72.pth exists in /home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune
Successfully dumped yolov3_mobilenetv2_320_300e_coco.py to /home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune
load checkpoint from local path: yolov3_mobilenetv2_320_300e_coco_20210719_215349-d18dff72.pth
The model and loaded state dict do not match exactly

size mismatch for bbox_head.convs_pred.0.weight: copying a param with shape torch.Size([255, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([18, 96, 1, 1]).
size mismatch for bbox_head.convs_pred.0.bias: copying a param with shape torch.Size([255]) from checkpoint, the shape in current model is torch.Size([18]).
size mismatch for bbox_head.convs_pred.1.weight: copying a param with shape torch.Size([255, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([18, 96, 1, 1]).
size mismatch for bbox_head.convs_pred.1.bias: copying a param with shape torch.Size([255]) from checkpoint, the shape in current model is torch.Size([18]).
size mismatch for bbox_head.convs_pred.2.weight: copying a param with shape torch.Size([255, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([18, 96, 1, 1]).
size mismatch for bbox_head.convs_pred.2.bias: copying a param with shape torch.Size([255]) from checkpoint, the shape in current model is torch.Size([18]).





We set the learning rate to be 2e-4. Note that we use a two-stage
learning rate option during finetuning by default, and the model head
will have 100x learning rate. Using a two-stage learning rate with high
learning rate only on head layers makes the model converge faster during
finetuning. It usually gives better performance as well, especially on
small datasets with hundreds or thousands of images. We also set the
epoch to be 30 for fast finetuning and batch_size to be 32. We also
compute the time of the fit process here for better understanding the
speed.


import time
start = time.time()
predictor.fit(
    train_path,
    hyperparameters={
        "optimization.learning_rate": 2e-4, # we use two stage and detection head has 100x lr
        "optimization.max_epochs": 30,
        "env.per_gpu_batch_size": 32,  # decrease it when model is large
    },
)
end = time.time()





Using default root folder: ./pothole/pothole/Annotations/... Specify root=... if you feel it is wrong...
Global seed set to 123
No path specified. Models will be saved in: "AutogluonModels/ag-20230214_015606/"


loading annotations into memory...
Done (t=0.00s)
creating index...
index created!





AutoMM starts to create your model. ✨

- Model will be saved to "/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606".

- Validation metric is "map".

- To track the learning progress, you can open a terminal and launch Tensorboard:
    `shell
    # Assume you have installed tensorboard
    tensorboard --logdir /home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606
    `

Enjoy your coffee, and let AutoMM do the job ☕☕☕ Learn more at https://auto.gluon.ai

/home/ci/opt/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py:577: LightningDeprecationWarning: The Trainer argument auto_select_gpus has been deprecated in v1.9.0 and will be removed in v2.0.0. Please use the function pytorch_lightning.accelerators.find_usable_cuda_devices instead.
  rank_zero_deprecation(
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
HPU available: False, using: 0 HPUs
Trainer(val_check_interval=1.0) was configured so validation will run at the end of the training epoch..
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name              | Type                             | Params
-----------------------------------------------------------------------
0 | model             | MMDetAutoModelForObjectDetection | 3.7 M
1 | validation_metric | MeanAveragePrecision             | 0
-----------------------------------------------------------------------
3.7 M     Trainable params
0         Non-trainable params
3.7 M     Total params
14.675    Total estimated model params size (MB)
Epoch 2, global step 9: 'val_map' reached 0.00517 (best 0.00517), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606/epoch=2-step=9.ckpt' as top 1
Epoch 5, global step 18: 'val_map' reached 0.06065 (best 0.06065), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606/epoch=5-step=18.ckpt' as top 1
Epoch 8, global step 27: 'val_map' reached 0.14553 (best 0.14553), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606/epoch=8-step=27.ckpt' as top 1
Epoch 11, global step 36: 'val_map' reached 0.18481 (best 0.18481), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606/epoch=11-step=36.ckpt' as top 1
Epoch 14, global step 45: 'val_map' reached 0.22442 (best 0.22442), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606/epoch=14-step=45.ckpt' as top 1
Epoch 17, global step 54: 'val_map' reached 0.25855 (best 0.25855), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606/epoch=17-step=54.ckpt' as top 1
Epoch 20, global step 63: 'val_map' reached 0.26429 (best 0.26429), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606/epoch=20-step=63.ckpt' as top 1
Epoch 23, global step 72: 'val_map' was not in top 1
Epoch 26, global step 81: 'val_map' was not in top 1
Epoch 29, global step 90: 'val_map' was not in top 1
Trainer.fit stopped: max_epochs=30 reached.
AutoMM has created your model 🎉🎉🎉

- To load the model, use the code below:
    `python
    from autogluon.multimodal import MultiModalPredictor
    predictor = MultiModalPredictor.load("/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606")
    `

- You can open a terminal and launch Tensorboard to visualize the training log:
    `shell
    # Assume you have installed tensorboard
    tensorboard --logdir /home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015606
    `

- If you are not satisfied with the model, try to increase the training time,
adjust the hyperparameters (https://auto.gluon.ai/stable/tutorials/multimodal/advanced_topics/customization.html),
or post issues on GitHub: https://github.com/autogluon/autogluon


Print out the time and we can see that it’s fast!


print("This finetuning takes %.2f seconds." % (end - start))





This finetuning takes 158.85 seconds.





To evaluate the model we just trained, run:


predictor.evaluate(test_path)





Using default root folder: ./pothole/pothole/Annotations/... Specify root=... if you feel it is wrong...


loading annotations into memory...
Done (t=0.00s)
creating index...
index created!





/home/ci/opt/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py:577: LightningDeprecationWarning: The Trainer argument auto_select_gpus has been deprecated in v1.9.0 and will be removed in v2.0.0. Please use the function pytorch_lightning.accelerators.find_usable_cuda_devices instead.
  rank_zero_deprecation(
A new predictor save path is created.This is to prevent you to overwrite previous predictor saved here.You could check current save path at predictor._save_path.If you still want to use this path, set resume=True
No path specified. Models will be saved in: "AutogluonModels/ag-20230214_015846/"


saving file at /home/ci/autogluon/docs/_build/eval/tutorials/multimodal/object_detection/finetune/AutogluonModels/ag-20230214_015846/object_detection_result_cache.json
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Loading and preparing results...
DONE (t=0.01s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type bbox
DONE (t=0.24s).
Accumulating evaluation results...
DONE (t=0.04s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.225
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.536
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.047
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.220
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.390
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.171
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.343
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.390
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.237
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.393
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.509


{'map': 0.2252467580757856,
 'mean_average_precision': 0.2252467580757856,
 'map_50': 0.5361216854926647,
 'map_75': 0.17767789882203627,
 'map_small': 0.047494345058986594,
 'map_medium': 0.21996057096849003,
 'map_large': 0.390208121378859,
 'mar_1': 0.17138643067846607,
 'mar_10': 0.3427728613569322,
 'mar_100': 0.3902654867256637,
 'mar_small': 0.23661971830985915,
 'mar_medium': 0.3933701657458563,
 'mar_large': 0.5091954022988506}





And the evaluation results are shown in command line output. The first
value is mAP in COCO standard, and the second one is mAP in VOC standard
(or mAP50). For more details about these metrics, see COCO’s evaluation
guideline.


We can get the prediction on test set:


pred = predictor.predict(test_path)





Using default root folder: ./pothole/pothole/Annotations/... Specify root=... if you feel it is wrong...


loading annotations into memory...
Done (t=0.00s)
creating index...
index created!





/home/ci/opt/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py:577: LightningDeprecationWarning: The Trainer argument auto_select_gpus has been deprecated in v1.9.0 and will be removed in v2.0.0. Please use the function pytorch_lightning.accelerators.find_usable_cuda_devices instead.
  rank_zero_deprecation(


Let’s also visualize the prediction result:


!pip install opencv-python





Requirement already satisfied: opencv-python in /home/ci/opt/venv/lib/python3.8/site-packages (4.7.0.68)
Requirement already satisfied: numpy>=1.17.0 in /home/ci/opt/venv/lib/python3.8/site-packages (from opencv-python) (1.23.5)





from autogluon.multimodal.utils import visualize_detection
conf_threshold = 0.25  # Specify a confidence threshold to filter out unwanted boxes
visualization_result_dir = "./"  # Use the pwd as result dir to save the visualized image
visualized = visualize_detection(
    pred=pred[12:13],
    detection_classes=predictor.get_predictor_classes(),
    conf_threshold=conf_threshold,
    visualization_result_dir=visualization_result_dir,
)
from PIL import Image
from IPython.display import display
img = Image.fromarray(visualized[0][:, :, ::-1], 'RGB')
display(img)





Saved visualizations to ./






../../../../_images/output_detection_fast_finetune_coco_631583_22_1.png



Under this fast finetune setting, we reached a good mAP number on a new
dataset with a few hundred seconds! For how to finetune with higher
performance, see AutoMM Detection - High Performance Finetune on COCO Format Dataset, where we
finetuned a VFNet model with 5 hours and reached
mAP = 0.450, mAP50 = 0.718 on this dataset.




Other Examples


You may go to AutoMM
Examples
to explore other examples about AutoMM.






Customization


To learn how to customize AutoMM, please refer to
Customize AutoMM.






Citation


@misc{redmon2018yolov3,
    title={YOLOv3: An Incremental Improvement},
    author={Joseph Redmon and Ali Farhadi},
    year={2018},
    eprint={1804.02767},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}