![]() usr/local/lib/python3.7/dist-packages/torch/optim/lr_scheduler.py:134: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. 09:37:13 - Uses CosineAnnealingLR scheduler. 09:37:13 - Learning rate: 0.01, Base net learning rate: 0.001, Extra Layers learning rate: 0.01. 09:37:03 - Took 0.10 seconds to load the model. 09:37:03 - Init from pretrained ssd models/mobilenet-v1-ssd-mp-0_675.pth 09:37:02 - Dataset Summary:Number of Images: 255 09:37:02 - annotations loaded from: data/airobject/sub-test-annotations-bbox.csv 09:37:02 - loading annotations from: data/airobject/sub-test-annotations-bbox.csv 09:37:02 - Stored labels into file models/airobject/labels.txt. 09:37:02 - Dataset Summary:Number of Images: 1661 09:37:00 - annotations loaded from: data/airobject/sub-train-annotations-bbox.csv 09:37:00 - loading annotations from: data/airobject/sub-train-annotations-bbox.csv 09:37:00 - Namespace(balance_data=False, base_net=None, base_net_lr=0.001, batch_size=20, checkpoint_folder='models/airobject', dataset_type='open_images', datasets=, debug_steps=10, extra_layers_lr=None, freeze_base_net=False, freeze_net=False, gamma=0.1, lr=0.01, mb2_width_mult=1.0, milestones='80,100', momentum=0.9, net='mb1-ssd', num_epochs=5, num_workers=2, pretrained_ssd='models/mobilenet-v1-ssd-mp-0_675.pth', resume=None, scheduler='cosine', t_max=100, use_cuda=True, validation_epochs=1, weight_decay=0.0005) !python3 train_ssd.py -data=data/airobject -model-dir=models/airobject -batch-size=20 -epochs=5 !wget -O models/mobilenet-v1-ssd-mp-0_675.pthĮxecute Re-trainig This time, to save time, I set the number of Epoch to 5. 09:13:42 - Starting to download 1998 images.įirst, download the trained model. 09:13:42 - Saving 'test' data to data/airobject/sub-test-annotations-bbox.csv. 09:13:42 - Saving 'validation' data to data/airobject/sub-validation-annotations-bbox.csv. 09:13:42 - Saving 'train' data to data/airobject/sub-train-annotations-bbox.csv. 09:13:42 - Limiting test dataset to: 255 images (362 boxes) 09:13:42 - Limiting validation dataset to: 82 images (115 boxes) 09:13:40 - Read annotation file data/airobject/test-annotations-bbox.csv 09:13:40 - Available validation boxes: 2238 09:13:40 - Available validation images: 1551 09:13:40 - Read annotation file data/airobject/validation-annotations-bbox.csv 09:13:21 - Read annotation file data/airobject/train-annotations-bbox.csv 09:13:21 - Requested 4 classes, found 4 classes The image download was completed without any problems. !python3 open_images_downloader.py -max-images=2000 -class-names "Aircraft","Airplane","Bird","Helicopter" -data=data/airobject This time, instead of downloading all 37584 images in 4 classes, I try to limited download to 2000 images in consideration of time and storage size. 09:03:28 - Total available images: 37584īounding box count: 77415 Downloading OpenImages with a limited number of images ![]() 09:03:26 - Read annotation file data/airobject/test-annotations-bbox.csv 09:03:24 - Available validation boxes: 2238 09:03:24 - Available validation images: 1551 ![]() 09:03:23 - Read annotation file data/airobject/validation-annotations-bbox.csv 09:03:02 - Read annotation file data/airobject/train-annotations-bbox.csv 09:02:36 - Requested 4 classes, found 4 classes When I checked the execution results, I found that there were a total of 37584 Images and 77415 Boundingn Box Clounts in 4 classes in advance. !python3 open_images_downloader.py -stats-only -class-names "Aircraft","Airplane","Bird","Helicopter" -data=data/airobject Learn about four classes, “Aircraft”, “Airplane”, “Bird”, and “Helicopter” from 601 types.īy adding option –status-only, you can know the number of data before actually downloading the Image.
0 Comments
Leave a Reply. |