Bounding box (-157,-92,-101,53) is completely outside the image and will not be drawn

[xinyuecai2016]

Hello friends， My OS is Ubuntu16.04 LTS, and When I run the command "./script/train 0 8" on dataset icdar2015, I found that it would be output like this, 2018-05-06 16:24:15.192086: W tensorflow/core/kernels/draw_bounding_box_op.cc:116] Bounding box (-157,-92,-101,53) is completely outside the image and will not be drawn.

2018-05-06 16:24:15.192152: W tensorflow/core/kernels/draw_bounding_box_op.cc:116] Bounding box (-211,3,-195,34) is completely outside the image and will not be drawn.

2018-05-06 16:24:15.192159: W tensorflow/core/kernels/draw_bounding_box_op.cc:116] Bounding box (-153,196,-112,266) is completely outside the image and will not be drawn.

After checked the code, I found that when preprocessing image(line130 in train_pixel_link.py), the function distorted_bounding_box_crop() was called, but the function bboxes_filter_overlap() was suppressed by the parameter assign_value=LABEL_IGNORE. So these outside bboxes would not be filtered, and the output would generate like this.

The question I want to ask is that why not filter the bboxes outside the croped picture?

[dengdan]

Because filtering them away or not does not make any difference on the training process, except for the displayed logging msg. You can do it if you want, and a pull request is welcome.

[alpace]

2019-03-16 09:41:40.475868: I tensorflow/core/common_runtime/gpu/gpu_device.cc:887] Found device 0 with properties: name: Quadro M2000 major: 5 minor: 2 memoryClockRate (GHz) 1.1625 pciBusID 0000:04:00.0 Total memory: 3.95GiB Free memory: 2.79GiB 2019-03-16 09:41:40.475916: I tensorflow/core/common_runtime/gpu/gpu_device.cc:908] DMA: 0 2019-03-16 09:41:40.475930: I tensorflow/core/common_runtime/gpu/gpu_device.cc:918] 0: Y 2019-03-16 09:41:40.475946: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: Quadro M2000, pci bus id: 0000:04:00.0) INFO:tensorflow:Restoring parameters from ./models/icdar2015/model.ckpt-0 2019-03-16 09:41:43.114186: I tensorflow/core/common_runtime/simple_placer.cc:669] Ignoring device specification /device:GPU:0 for node 'clone_0/fifo_queue_Dequeue' because the input edge from 'icdar2015_prefetch_queue/prefetch_queue/fifo_queue' is a reference connection and already has a device field set to /device:CPU:0 INFO:tensorflow:Starting Session. INFO:tensorflow:Starting Queues. INFO:tensorflow:global_step/sec: 0 2019-03-16 09:42:05.462899: W tensorflow/core/kernels/draw_bounding_box_op.cc:122] Bounding box (92,-87,128,-77) is completely outside the image and will not be drawn. 2019-03-16 09:42:05.462944: W tensorflow/core/kernels/draw_bounding_box_op.cc:122] Bounding box (-16,75,-4,90) is completely outside the image and will not be drawn. 2019-03-16 09:42:05.462956: W tensorflow/core/kernels/draw_bounding_box_op.cc:122] Bounding box (-27,-48,-15,-37) is completely outside the image and will not be drawn. 2019-03-16 09:42:05.474938: W tensorflow/core/kernels/draw_bounding_box_op.cc:122] Bounding box (92,-87,128,-77) is completely outside the image and will not be drawn. 2019-03-16 09:42:05.475122: W tensorflow/core/kernels/draw_bounding_box_op.cc:122] Bounding box (-16,75,-4,90) is completely outside the image and will not be drawn. 2019-03-16 09:42:05.475224: W tensorflow/core/kernels/draw_bounding_box_op.cc:122] Bounding box (-27,-48,-15,-37) is completely outside the image and will not be drawn. 2019-03-16 09:42:06.839645: E tensorflow/stream_executor/cuda/cuda_dnn.cc:359] could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-03-16 09:42:06.839699: E tensorflow/stream_executor/cuda/cuda_dnn.cc:326] could not destroy cudnn handle: CUDNN_STATUS_BAD_PARAM 2019-03-16 09:42:06.839718: F tensorflow/core/kernels/conv_ops.cc:659] Check failed: stream->parent()->GetConvolveAlgorithms(&algorithms) ./scripts/train.sh: 行 37: 136261 已放弃 (核心已转储)

training error,