vikrant7 / mobile-vod-bottleneck-lstm

Implementation of Mobile Video Object Detection with Temporally-Aware Feature Maps using PyTorch
131 stars 37 forks source link

error in calculating error #17

Open AmitYadu opened 4 years ago

AmitYadu commented 4 years ago

2020-02-19 06:11:13,289 - root - INFO - Use Cuda. 2020-02-19 06:11:13,289 - root - INFO - Namespace(base_net_lr=None, batch_size=10, cache_path=None, checkpoint_folder='models/', datasets='./datasets/ILSVRC2015/', debug_steps=100, freeze_net=True, gamma=0.1, lr=0.0003, milestones='80,100', momentum=0.9, num_epochs=1, num_workers=1, pretrained='./models/basenet/WM-1.0-Epoch-29-Loss-166.12886941432953.pth', resume=None, scheduler='multi-step', sequence_length=5, ssd_lr=None, t_max=120, use_cuda=True, validation_epochs=5, weight_decay=0.0005, width_mult=1.0) 2020-02-19 06:11:13,290 - root - INFO - Prepare training datasets. class 2020-02-19 06:11:13,292 - root - INFO - using default Imagenet VID classes. 2020-02-19 06:11:13,350 - root - INFO - gt roidb loaded from datasets/ILSVRC2015/train_VID_seq_gt_db.pkl 2020-02-19 06:11:13,352 - root - INFO - Stored labels into file models/vid-model-labels.txt. 2020-02-19 06:11:13,352 - root - INFO - Train dataset size: 330 2020-02-19 06:11:13,352 - root - INFO - Prepare Validation datasets. class 2020-02-19 06:11:13,353 - root - INFO - using default Imagenet VID classes. 2020-02-19 06:11:13,354 - root - INFO - gt roidb loaded from datasets/ILSVRC2015/val_VID_seq_gt_db.pkl 2020-02-19 06:11:13,354 - root - INFO - <datasets.vid_dataset_new.VIDDataset object at 0x7f4bee441fd0> 2020-02-19 06:11:13,354 - root - INFO - validation dataset size: 0 2020-02-19 06:11:13,354 - root - INFO - Build network. 2020-02-19 06:11:13,371 - root - INFO - Initializing weights of base net 2020-02-19 06:11:13,390 - root - INFO - Initializing weights of lstm 2020-02-19 06:11:17,248 - root - INFO - Initializing weights of SSD 2020-02-19 06:11:17,260 - root - INFO - Loading weights from pretrained netwok 2020-02-19 06:11:17,316 - root - INFO - Freeze net. 2020-02-19 06:11:17,327 - root - INFO - Learning rate: 0.0003, Base net learning rate: 0.0003, Extra Layers learning rate: 0.0003. 2020-02-19 06:11:17,327 - root - INFO - Start training from epoch 0. /usr/local/lib/python3.6/dist-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead. warnings.warn(warning.format(ret)) Traceback (most recent call last): File "train_mvod_lstm1.py", line 295, in val_loss, val_regression_loss, val_classification_loss = val(val_loader, net, criterion, DEVICE) File "train_mvod_lstm1.py", line 187, in val return running_loss / num, running_regression_loss / num, running_classification_loss / num ZeroDivisionError: float division by zero