[10/11 09:48:55 d2.engine.defaults]: Model:
GeneralizedRCNN(
(backbone): FPN(
(fpn_lateral2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(top_block): LastLevelMaxPool()
(bottom_up): ResNet(
(stem): BasicStem(
(conv1): Conv2d(
3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
)
(res2): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv1): Conv2d(
64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
)
(res3): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv1): Conv2d(
256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
)
(res4): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv1): Conv2d(
512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(4): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(5): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
)
(res5): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv1): Conv2d(
1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
)
)
)
(proposal_generator): RPN(
(anchor_generator): DefaultAnchorGenerator(
(cell_anchors): BufferList()
)
(rpn_head): StandardRPNHead(
(conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(objectness_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
(anchor_deltas): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
)
)
(roi_heads): StandardROIHeads(
(box_pooler): ROIPooler(
(level_poolers): ModuleList(
(0): ROIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, aligned=True)
(1): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
(2): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
(3): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
)
)
(box_head): FastRCNNConvFCHead(
(fc1): Linear(in_features=12544, out_features=1024, bias=True)
(fc2): Linear(in_features=1024, out_features=1024, bias=True)
)
(box_predictor): FastRCNNOutputLayers(
(cls_score): Linear(in_features=1024, out_features=2, bias=True)
(bbox_pred): Linear(in_features=1024, out_features=4, bias=True)
)
(mask_pooler): ROIPooler(
(level_poolers): ModuleList(
(0): ROIAlign(output_size=(14, 14), spatial_scale=0.25, sampling_ratio=0, aligned=True)
(1): ROIAlign(output_size=(14, 14), spatial_scale=0.125, sampling_ratio=0, aligned=True)
(2): ROIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
(3): ROIAlign(output_size=(14, 14), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
)
)
(mask_head): MaskRCNNConvUpsampleHead(
(mask_fcn1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_fcn2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_fcn3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_fcn4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
(predictor): Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
)
)
)
[10/11 09:48:57 d2.data.build]: Removed 0 images with no usable annotations. 61 images left.
[10/11 09:48:57 d2.data.build]: Distribution of training instances among all 1 categories:
| category | #instances |
|:----------:|:-------------|
| balloon | 255 |
| | |
[10/11 09:48:57 d2.data.detection_utils]: TransformGens used in training: [ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip()]
[10/11 09:48:57 d2.data.build]: Using training sampler TrainingSampler
[10/11 09:49:01 d2.engine.train_loop]: Starting training from iteration 0
[10/11 09:49:25 d2.utils.events]: eta: 0:05:35 iter: 19 total_loss: 2.006 loss_cls: 0.685 loss_box_reg: 0.608 loss_mask: 0.692 loss_rpn_cls: 0.021 loss_rpn_loc: 0.005 time: 1.2004 data_time: 0.0035 lr: 0.000005 max_mem: 2725M
[10/11 09:49:49 d2.utils.events]: eta: 0:05:07 iter: 39 total_loss: 2.141 loss_cls: 0.650 loss_box_reg: 0.658 loss_mask: 0.663 loss_rpn_cls: 0.040 loss_rpn_loc: 0.010 time: 1.2014 data_time: 0.0038 lr: 0.000010 max_mem: 2726M
[10/11 09:50:14 d2.utils.events]: eta: 0:04:53 iter: 59 total_loss: 1.734 loss_cls: 0.581 loss_box_reg: 0.583 loss_mask: 0.603 loss_rpn_cls: 0.018 loss_rpn_loc: 0.005 time: 1.2228 data_time: 0.0035 lr: 0.000015 max_mem: 2850M
[10/11 09:50:38 d2.utils.events]: eta: 0:04:26 iter: 79 total_loss: 1.721 loss_cls: 0.509 loss_box_reg: 0.633 loss_mask: 0.538 loss_rpn_cls: 0.033 loss_rpn_loc: 0.007 time: 1.2148 data_time: 0.0039 lr: 0.000020 max_mem: 2850M
[10/11 09:51:03 d2.utils.events]: eta: 0:04:04 iter: 99 total_loss: 1.681 loss_cls: 0.442 loss_box_reg: 0.700 loss_mask: 0.479 loss_rpn_cls: 0.031 loss_rpn_loc: 0.008 time: 1.2220 data_time: 0.0036 lr: 0.000025 max_mem: 2850M
[10/11 09:51:29 d2.utils.events]: eta: 0:03:42 iter: 119 total_loss: 1.519 loss_cls: 0.408 loss_box_reg: 0.611 loss_mask: 0.401 loss_rpn_cls: 0.028 loss_rpn_loc: 0.004 time: 1.2303 data_time: 0.0036 lr: 0.000030 max_mem: 2850M
[10/11 09:51:54 d2.utils.events]: eta: 0:03:18 iter: 139 total_loss: 1.490 loss_cls: 0.370 loss_box_reg: 0.696 loss_mask: 0.364 loss_rpn_cls: 0.018 loss_rpn_loc: 0.011 time: 1.2313 data_time: 0.0036 lr: 0.000035 max_mem: 2850M
[10/11 09:52:18 d2.utils.events]: eta: 0:02:53 iter: 159 total_loss: 1.293 loss_cls: 0.307 loss_box_reg: 0.611 loss_mask: 0.303 loss_rpn_cls: 0.021 loss_rpn_loc: 0.006 time: 1.2321 data_time: 0.0034 lr: 0.000040 max_mem: 2850M
[10/11 09:52:43 d2.utils.events]: eta: 0:02:30 iter: 179 total_loss: 1.221 loss_cls: 0.279 loss_box_reg: 0.629 loss_mask: 0.287 loss_rpn_cls: 0.024 loss_rpn_loc: 0.011 time: 1.2337 data_time: 0.0035 lr: 0.000045 max_mem: 2850M
[10/11 09:53:08 d2.utils.events]: eta: 0:02:05 iter: 199 total_loss: 1.203 loss_cls: 0.242 loss_box_reg: 0.639 loss_mask: 0.241 loss_rpn_cls: 0.020 loss_rpn_loc: 0.006 time: 1.2365 data_time: 0.0035 lr: 0.000050 max_mem: 2850M
[10/11 09:53:34 d2.utils.events]: eta: 0:01:40 iter: 219 total_loss: 1.109 loss_cls: 0.234 loss_box_reg: 0.659 loss_mask: 0.205 loss_rpn_cls: 0.015 loss_rpn_loc: 0.011 time: 1.2379 data_time: 0.0035 lr: 0.000055 max_mem: 2850M
[10/11 09:53:59 d2.utils.events]: eta: 0:01:16 iter: 239 total_loss: 1.023 loss_cls: 0.202 loss_box_reg: 0.596 loss_mask: 0.186 loss_rpn_cls: 0.021 loss_rpn_loc: 0.009 time: 1.2428 data_time: 0.0034 lr: 0.000060 max_mem: 2850M
[10/11 09:54:24 d2.utils.events]: eta: 0:00:51 iter: 259 total_loss: 0.989 loss_cls: 0.192 loss_box_reg: 0.599 loss_mask: 0.179 loss_rpn_cls: 0.020 loss_rpn_loc: 0.007 time: 1.2424 data_time: 0.0035 lr: 0.000065 max_mem: 2850M
[10/11 09:54:49 d2.utils.events]: eta: 0:00:26 iter: 279 total_loss: 0.944 loss_cls: 0.155 loss_box_reg: 0.564 loss_mask: 0.151 loss_rpn_cls: 0.026 loss_rpn_loc: 0.011 time: 1.2431 data_time: 0.0034 lr: 0.000070 max_mem: 2850M
[10/11 09:55:17 d2.utils.events]: eta: 0:00:01 iter: 299 total_loss: 0.761 loss_cls: 0.135 loss_box_reg: 0.468 loss_mask: 0.119 loss_rpn_cls: 0.017 loss_rpn_loc: 0.006 time: 1.2489 data_time: 0.0035 lr: 0.000075 max_mem: 2850M
[10/11 09:55:18 d2.engine.hooks]: Overall training speed: 297 iterations in 0:06:12 (1.2531 s / it)
[10/11 09:55:18 d2.engine.hooks]: Total training time: 0:06:14 (0:00:02 on hooks)
