.. _sec_object_detection_quick: Object Detection - Quick Start ============================== Object detection is the process of identifying and localizing objects in an image and is an important task in computer vision. Follow this tutorial to learn how to use AutoGluon for object detection. **Tip**: If you are new to AutoGluon, review :ref:`sec_imgquick` first to learn the basics of the AutoGluon API. Our goal is to detect motorbike in images by `YOLOv3 model `__. A tiny dataset is collected from VOC dataset, which only contains the motorbike category. The model pretrained on the COCO dataset is used to fine-tune our small dataset. With the help of AutoGluon, we are able to try many models with different hyperparameters automatically, and return the best one as our final model. To start, import ObjectDetector: .. code:: python from autogluon.vision import ObjectDetector .. parsed-literal:: :class: output /var/lib/jenkins/miniconda3/envs/autogluon-tutorial-object-detection-v3/lib/python3.9/site-packages/gluoncv/__init__.py:40: UserWarning: Both `mxnet==1.9.1` and `torch==1.10.2+cu102` are installed. You might encounter increased GPU memory footprint if both framework are used at the same time. warnings.warn(f'Both `mxnet=={mx.__version__}` and `torch=={torch.__version__}` are installed. ' Tiny\_motorbike Dataset ----------------------- We collect a toy dataset for detecting motorbikes in images. From the VOC dataset, images are randomly selected for training, validation, and testing - 120 images for training, 50 images for validation, and 50 for testing. This tiny dataset follows the same format as VOC. Using the commands below, we can download this dataset, which is only 23M. The name of unzipped folder is called ``tiny_motorbike``. Anyway, the task dataset helper can perform the download and extraction automatically, and load the dataset according to the detection formats. .. code:: python url = 'https://autogluon.s3.amazonaws.com/datasets/tiny_motorbike.zip' dataset_train = ObjectDetector.Dataset.from_voc(url, splits='trainval') .. parsed-literal:: :class: output tiny_motorbike/ ├── Annotations/ ├── ImageSets/ └── JPEGImages/ Fit Models by AutoGluon ----------------------- In this section, we demonstrate how to apply AutoGluon to fit our detection models. We use mobilenet as the backbone for the YOLOv3 model. Two different learning rates are used to fine-tune the network. The best model is the one that obtains the best performance on the validation dataset. You can also try using more networks and hyperparameters to create a larger searching space. We ``fit`` a classifier using AutoGluon as follows. In each experiment (one trial in our searching space), we train the model for 5 epochs to avoid bursting our tutorial runtime. .. code:: python time_limit = 60*30 # at most 0.5 hour detector = ObjectDetector() hyperparameters = {'epochs': 5, 'batch_size': 8} hyperparameter_tune_kwargs={'num_trials': 2} detector.fit(dataset_train, time_limit=time_limit, hyperparameters=hyperparameters, hyperparameter_tune_kwargs=hyperparameter_tune_kwargs) .. parsed-literal:: :class: output ============================================================================= WARNING: ObjectDetector is deprecated as of v0.4.0 and may contain various bugs and issues! In a future release ObjectDetector may be entirely reworked to use Torch as a backend. This future change will likely be API breaking.Users should ensure they update their code that depends on ObjectDetector when upgrading to future AutoGluon releases. For more information, refer to ObjectDetector refactor GitHub issue: https://github.com/awslabs/autogluon/issues/1559 ============================================================================= The number of requested GPUs is greater than the number of available GPUs.Reduce the number to 1 Randomly split train_data into train[148]/validation[22] splits. Starting HPO experiments .. parsed-literal:: :class: output 0%| | 0/2 [00:00 != ): { root.dataset_root ~/.mxnet/datasets/ != auto root.dataset voc_tiny != auto root.train.batch_size 16 != 8 root.train.early_stop_patience -1 != 10 root.train.epochs 20 != 5 root.train.early_stop_baseline 0.0 != -inf root.train.early_stop_max_value 1.0 != inf root.train.seed 233 != 409 root.gpus (0, 1, 2, 3) != (0,) root.num_workers 4 != 8 root.ssd.base_network vgg16_atrous != resnet50_v1 root.ssd.data_shape 300 != 512 root.valid.batch_size 16 != 8 } Saved config to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-object-detection-v3/docs/_build/eval/tutorials/object_detection/056ec2db/.trial_0/config.yaml No gpu detected, fallback to cpu. You can ignore this warning if this is intended. Using transfer learning from ssd_512_resnet50_v1_coco, the other network parameters are ignored. Start training from [Epoch 0] [Epoch 0] Training cost: 66.784484, CrossEntropy=3.814896, SmoothL1=1.099648 [Epoch 0] Validation: chair=nan person=0.7144378731393329 bicycle=nan car=0.6704085780091742 motorbike=0.790986790986791 boat=nan dog=nan pottedplant=0.00802139037433155 cow=nan bus=nan mAP=0.5459636581274074 [Epoch 0] Current best map: 0.545964 vs previous 0.000000, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-object-detection-v3/docs/_build/eval/tutorials/object_detection/056ec2db/.trial_0/best_checkpoint.pkl [Epoch 1] Training cost: 70.069097, CrossEntropy=2.816050, SmoothL1=1.203322 [Epoch 1] Validation: chair=nan person=0.692227001368942 bicycle=nan car=0.6193495052830091 motorbike=0.7381777757438465 boat=nan dog=nan pottedplant=0.0 cow=nan bus=nan mAP=0.5124385705989494 [Epoch 2] Training cost: 65.953285, CrossEntropy=2.473636, SmoothL1=1.084630 [Epoch 2] Validation: chair=nan person=0.6886954658844611 bicycle=nan car=0.6818181818181819 motorbike=0.7078637271819092 boat=nan dog=nan pottedplant=0.0 cow=nan bus=nan mAP=0.519594343721138 [Epoch 3] Training cost: 68.609943, CrossEntropy=2.229116, SmoothL1=0.966308 [Epoch 3] Validation: chair=nan person=0.6564136620954802 bicycle=nan car=1.0000000000000002 motorbike=0.823500216930344 boat=nan dog=nan pottedplant=0.0 cow=nan bus=nan mAP=0.6199784697564561 [Epoch 3] Current best map: 0.619978 vs previous 0.545964, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-object-detection-v3/docs/_build/eval/tutorials/object_detection/056ec2db/.trial_0/best_checkpoint.pkl [Epoch 4] Training cost: 65.505345, CrossEntropy=2.193415, SmoothL1=0.978995 [Epoch 4] Validation: chair=nan person=0.6915480604152169 bicycle=nan car=0.7234848484848485 motorbike=0.8010638010638009 boat=nan dog=nan pottedplant=0.0 cow=nan bus=nan mAP=0.5540241774909667 Applying the state from the best checkpoint... Finished, total runtime is 386.28 s { 'best_config': { 'dataset': 'auto', 'dataset_root': 'auto', 'estimator': , 'gpus': [0], 'horovod': False, 'num_workers': 8, 'resume': '', 'save_interval': 1, 'ssd': { 'amp': False, 'base_network': 'resnet50_v1', 'data_shape': 512, 'filters': None, 'nms_thresh': 0.45, 'nms_topk': 400, 'ratios': ( [1, 2, 0.5], [1, 2, 0.5, 3, 0.3333333333333333], [1, 2, 0.5, 3, 0.3333333333333333], [1, 2, 0.5, 3, 0.3333333333333333], [1, 2, 0.5], [1, 2, 0.5]), 'sizes': (30, 60, 111, 162, 213, 264, 315), 'steps': (8, 16, 32, 64, 100, 300), 'syncbn': False, 'transfer': 'ssd_512_resnet50_v1_coco'}, 'train': { 'batch_size': 8, 'dali': False, 'early_stop_baseline': -inf, 'early_stop_max_value': inf, 'early_stop_min_delta': 0.001, 'early_stop_patience': 10, 'epochs': 5, 'log_interval': 100, 'lr': 0.001, 'lr_decay': 0.1, 'lr_decay_epoch': (160, 200), 'momentum': 0.9, 'seed': 409, 'start_epoch': 0, 'wd': 0.0005}, 'valid': { 'batch_size': 8, 'iou_thresh': 0.5, 'metric': 'voc07', 'val_interval': 1}}, 'total_time': 386.2827181816101, 'train_map': 0.7272349653862946, 'valid_map': 0.6199784697564561} .. parsed-literal:: :class: output Note that ``num_trials=2`` above is only used to speed up the tutorial. In normal practice, it is common to only use ``time_limit`` and drop ``num_trials``. Also note that hyperparameter tuning defaults to random search. After fitting, AutoGluon automatically returns the best model among all models in the searching space. From the output, we know the best model is the one trained with the second learning rate. To see how well the returned model performed on test dataset, call detector.evaluate(). .. code:: python dataset_test = ObjectDetector.Dataset.from_voc(url, splits='test') test_map = detector.evaluate(dataset_test) print("mAP on test dataset: {}".format(test_map[1][-1])) .. parsed-literal:: :class: output tiny_motorbike/ ├── Annotations/ ├── ImageSets/ └── JPEGImages/ mAP on test dataset: 0.5663367140669382 Below, we randomly select an image from test dataset and show the predicted class, box and probability over the origin image, stored in ``predict_class``, ``predict_rois`` and ``predict_score`` columns, respectively. You can interpret ``predict_rois`` as a dict of (``xmin``, ``ymin``, ``xmax``, ``ymax``) proportional to original image size. .. code:: python image_path = dataset_test.iloc[0]['image'] result = detector.predict(image_path) print(result) .. parsed-literal:: :class: output predict_class predict_score \ 0 motorbike 0.993426 1 person 0.984185 2 car 0.750799 3 car 0.169281 4 motorbike 0.165467 .. ... ... 67 car 0.023269 68 car 0.023256 69 person 0.023089 70 car 0.023036 71 car 0.023034 predict_rois 0 {'xmin': 0.31400594115257263, 'ymin': 0.423492... 1 {'xmin': 0.40062546730041504, 'ymin': 0.297083... 2 {'xmin': 0.0, 'ymin': 0.6154444813728333, 'xma... 3 {'xmin': 0.7174825668334961, 'ymin': 0.3963941... 4 {'xmin': 0.0, 'ymin': 0.6185303926467896, 'xma... .. ... 67 {'xmin': 0.6949290633201599, 'ymin': 0.4761260... 68 {'xmin': 0.03558524325489998, 'ymin': 0.368901... 69 {'xmin': 0.1387866586446762, 'ymin': 0.8483116... 70 {'xmin': 0.0, 'ymin': 0.7108750343322754, 'xma... 71 {'xmin': 0.053460072726011276, 'ymin': 0.40237... [72 rows x 3 columns] Prediction with multiple images is permitted: .. code:: python bulk_result = detector.predict(dataset_test) print(bulk_result) .. parsed-literal:: :class: output predict_class predict_score \ 0 motorbike 0.993426 1 person 0.984185 2 car 0.750799 3 car 0.169281 4 motorbike 0.165467 ... ... ... 4331 person 0.030525 4332 person 0.030276 4333 person 0.030247 4334 person 0.030156 4335 chair 0.030064 predict_rois \ 0 {'xmin': 0.31400594115257263, 'ymin': 0.423492... 1 {'xmin': 0.40062546730041504, 'ymin': 0.297083... 2 {'xmin': 0.0, 'ymin': 0.6154444813728333, 'xma... 3 {'xmin': 0.7174825668334961, 'ymin': 0.3963941... 4 {'xmin': 0.0, 'ymin': 0.6185303926467896, 'xma... ... ... 4331 {'xmin': 0.5849460363388062, 'ymin': 0.0757173... 4332 {'xmin': 0.39304789900779724, 'ymin': 0.002860... 4333 {'xmin': 0.8782337307929993, 'ymin': 0.3585894... 4334 {'xmin': 0.9024809002876282, 'ymin': 0.1144954... 4335 {'xmin': 0.3000996708869934, 'ymin': 0.2109396... image 0 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 1 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 2 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 3 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 4 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... ... ... 4331 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 4332 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 4333 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 4334 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... 4335 /var/lib/jenkins/.gluoncv/datasets/tiny_motorb... [4336 rows x 4 columns] We can also save the trained model, and use it later. .. code:: python savefile = 'detector.ag' detector.save(savefile) new_detector = ObjectDetector.load(savefile) .. parsed-literal:: :class: output /var/lib/jenkins/miniconda3/envs/autogluon-tutorial-object-detection-v3/lib/python3.9/site-packages/mxnet/gluon/block.py:1784: UserWarning: Cannot decide type for the following arguments. Consider providing them as input: data: None input_sym_arg_type = in_param.infer_type()[0]