Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- dp92@dp92-System-Product-Name:~/Desktop/deep-stereo$ python Stereo_Online_Adaptation.py -l ~/Desktop/deep-stereo/data/kitti/list.txt -o ~/Desktop/deep-stereo/outputs --weights ~/Desktop/deep-stereo/pretrained/MADNet/kitti/weights.ckpt --modelName MADNet --blockConfig ~/Desktop/deep-stereo/block_config/MadNet_full.json --mode MAD --sampleMode PROBABILITY
- /anaconda3/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
- from ._conv import register_converters as _register_converters
- WARNING:tensorflow:From /home/dp92/Desktop/deep-stereo/Data_utils/data_reader.py:137: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
- Instructions for updating:
- Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
- WARNING:tensorflow:From /home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/training/input.py:188: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
- Instructions for updating:
- Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensors(tensor).repeat(num_epochs)`.
- WARNING:tensorflow:From /home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
- Instructions for updating:
- To construct input pipelines, use the `tf.data` module.
- WARNING:tensorflow:From /home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/training/input.py:197: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
- Instructions for updating:
- To construct input pipelines, use the `tf.data` module.
- WARNING:tensorflow:From /home/dp92/Desktop/deep-stereo/Data_utils/data_reader.py:166: batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
- Instructions for updating:
- Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.batch(batch_size)` (or `padded_batch(...)` if `dynamic_pad=True`).
- ==================================================
- Starting Creation of MADNet
- ==================================================
- WARNING: flag for trainign not setted, using default False
- WARNING: warping flag not setted, setting default True value
- WARNING: context_net flag not setted, setting default True value
- WARNING: radius_d not setted, setting default value 2
- WARNING: stride not setted, setting default value 1
- Args Validated, setting up graph
- Meta op to preprocess data created
- Network ready
- ==================================================
- Stereo Prediction Model:
- Layer left/conv1: (1, 160, 608, 16)
- Layer left/conv2: (1, 160, 608, 16)
- Layer left/conv3: (1, 80, 304, 32)
- Layer left/conv4: (1, 80, 304, 32)
- Layer left/conv5: (1, 40, 152, 64)
- Layer left/conv6: (1, 40, 152, 64)
- Layer left/conv7: (1, 20, 76, 96)
- Layer left/conv8: (1, 20, 76, 96)
- Layer left/conv9: (1, 10, 38, 128)
- Layer left/conv10: (1, 10, 38, 128)
- Layer left/conv11: (1, 5, 19, 192)
- Layer left/conv12: (1, 5, 19, 192)
- Layer right/conv1: (1, 160, 608, 16)
- Layer right/conv2: (1, 160, 608, 16)
- Layer right/conv3: (1, 80, 304, 32)
- Layer right/conv4: (1, 80, 304, 32)
- Layer right/conv5: (1, 40, 152, 64)
- Layer right/conv6: (1, 40, 152, 64)
- Layer right/conv7: (1, 20, 76, 96)
- Layer right/conv8: (1, 20, 76, 96)
- Layer right/conv9: (1, 10, 38, 128)
- Layer right/conv10: (1, 10, 38, 128)
- Layer right/conv11: (1, 5, 19, 192)
- Layer right/conv12: (1, 5, 19, 192)
- Layer fgc-volume-filtering-6/disp1: (1, 5, 19, 128)
- Layer fgc-volume-filtering-6/disp2: (1, 5, 19, 128)
- Layer fgc-volume-filtering-6/disp3: (1, 5, 19, 96)
- Layer fgc-volume-filtering-6/disp4: (1, 5, 19, 64)
- Layer fgc-volume-filtering-6/disp5: (1, 5, 19, 32)
- Layer fgc-volume-filtering-6/disp6: (1, 5, 19, 1)
- Layer fgc-volume-filtering-5/disp1: (1, 10, 38, 128)
- Layer fgc-volume-filtering-5/disp2: (1, 10, 38, 128)
- Layer fgc-volume-filtering-5/disp3: (1, 10, 38, 96)
- Layer fgc-volume-filtering-5/disp4: (1, 10, 38, 64)
- Layer fgc-volume-filtering-5/disp5: (1, 10, 38, 32)
- Layer fgc-volume-filtering-5/disp6: (1, 10, 38, 1)
- Layer fgc-volume-filtering-4/disp1: (1, 20, 76, 128)
- Layer fgc-volume-filtering-4/disp2: (1, 20, 76, 128)
- Layer fgc-volume-filtering-4/disp3: (1, 20, 76, 96)
- Layer fgc-volume-filtering-4/disp4: (1, 20, 76, 64)
- Layer fgc-volume-filtering-4/disp5: (1, 20, 76, 32)
- Layer fgc-volume-filtering-4/disp6: (1, 20, 76, 1)
- Layer fgc-volume-filtering-3/disp1: (1, 40, 152, 128)
- Layer fgc-volume-filtering-3/disp2: (1, 40, 152, 128)
- Layer fgc-volume-filtering-3/disp3: (1, 40, 152, 96)
- Layer fgc-volume-filtering-3/disp4: (1, 40, 152, 64)
- Layer fgc-volume-filtering-3/disp5: (1, 40, 152, 32)
- Layer fgc-volume-filtering-3/disp6: (1, 40, 152, 1)
- Layer fgc-volume-filtering-2/disp1: (1, 80, 304, 128)
- Layer fgc-volume-filtering-2/disp2: (1, 80, 304, 128)
- Layer fgc-volume-filtering-2/disp3: (1, 80, 304, 96)
- Layer fgc-volume-filtering-2/disp4: (1, 80, 304, 64)
- Layer fgc-volume-filtering-2/disp5: (1, 80, 304, 32)
- Layer fgc-volume-filtering-2/disp6: (1, 80, 304, 1)
- Layer context1: (1, 80, 304, 128)
- Layer context2: (1, 80, 304, 128)
- Layer context3: (1, 80, 304, 128)
- Layer context4: (1, 80, 304, 96)
- Layer context5: (1, 80, 304, 64)
- Layer context6: (1, 80, 304, 32)
- Layer context7: (1, 80, 304, 1)
- Layer final_disp: (1, 80, 304, 1)
- Prediction Layer rescaled_prediction: (1, 320, 1216, 1)
- Build train ops for disparity 0
- Going to train on ['fgc-volume-filtering-6/disp1', 'fgc-volume-filtering-6/disp2', 'fgc-volume-filtering-6/disp3', 'fgc-volume-filtering-6/disp4', 'fgc-volume-filtering-6/disp5', 'fgc-volume-filtering-6/disp6', 'left/conv12', 'left/conv11']
- Number of variable to train: 16
- Done
- ==================================================
- Build train ops for disparity 1
- Going to train on ['fgc-volume-filtering-5/disp1', 'fgc-volume-filtering-5/disp2', 'fgc-volume-filtering-5/disp3', 'fgc-volume-filtering-5/disp4', 'fgc-volume-filtering-5/disp5', 'fgc-volume-filtering-5/disp6', 'left/conv10', 'left/conv9']
- Number of variable to train: 16
- Done
- ==================================================
- Build train ops for disparity 2
- Going to train on ['fgc-volume-filtering-4/disp1', 'fgc-volume-filtering-4/disp2', 'fgc-volume-filtering-4/disp3', 'fgc-volume-filtering-4/disp4', 'fgc-volume-filtering-4/disp5', 'fgc-volume-filtering-4/disp6', 'left/conv8', 'left/conv7']
- Number of variable to train: 16
- Done
- ==================================================
- Build train ops for disparity 3
- Going to train on ['fgc-volume-filtering-3/disp1', 'fgc-volume-filtering-3/disp2', 'fgc-volume-filtering-3/disp3', 'fgc-volume-filtering-3/disp4', 'fgc-volume-filtering-3/disp5', 'fgc-volume-filtering-3/disp6', 'left/conv6', 'left/conv5']
- Number of variable to train: 16
- Done
- ==================================================
- Build train ops for disparity 4
- Going to train on ['fgc-volume-filtering-2/disp1', 'fgc-volume-filtering-2/disp2', 'fgc-volume-filtering-2/disp3', 'fgc-volume-filtering-2/disp4', 'fgc-volume-filtering-2/disp5', 'fgc-volume-filtering-2/disp6', 'left/conv4', 'left/conv3', 'left/conv2', 'left/conv1', 'context1', 'context2', 'context3', 'context4', 'context5', 'context6', 'context7']
- Number of variable to train: 34
- Done
- ==================================================
- 2018-12-02 16:00:52.566854: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
- 2018-12-02 16:00:52.660504: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:964] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
- 2018-12-02 16:00:52.660863: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties:
- name: GeForce GTX 1070 major: 6 minor: 1 memoryClockRate(GHz): 1.7845
- pciBusID: 0000:01:00.0
- totalMemory: 7.93GiB freeMemory: 7.34GiB
- 2018-12-02 16:00:52.660891: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0
- 2018-12-02 16:00:52.840854: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
- 2018-12-02 16:00:52.840895: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988] 0
- 2018-12-02 16:00:52.840901: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0: N
- 2018-12-02 16:00:52.841054: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7081 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)
- WARNING:tensorflow:From Stereo_Online_Adaptation.py:151: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
- Instructions for updating:
- To construct input pipelines, use the `tf.data` module.
- Disparity Net Restored?: True, number of restored variables: 98
- Step: 0 bad3:0.95 EPE:71.89 SSIM:0.10 f/b time:0.025095 Missing time:0:00:00.552091
- Exception catched FIFOQueue '_1_input_reader/batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)
- [[node input_reader/batch (defined at /home/dp92/Desktop/deep-stereo/Data_utils/data_reader.py:166) = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_FLOAT, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](input_reader/batch/fifo_queue, input_reader/batch/n)]]
- Caused by op 'input_reader/batch', defined at:
- File "Stereo_Online_Adaptation.py", line 328, in <module>
- main(args)
- File "Stereo_Online_Adaptation.py", line 44, in main
- shuffle=False
- File "/home/dp92/Desktop/deep-stereo/Data_utils/data_reader.py", line 126, in __init__
- self._build_input_pipeline()
- File "/home/dp92/Desktop/deep-stereo/Data_utils/data_reader.py", line 166, in _build_input_pipeline
- self._left_batch, self._right_batch, self._gt_batch = tf.train.batch([left_image, right_image, gt_image], self._batch_size, capacity=self._batch_size*20, num_threads=tt)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 306, in new_func
- return func(*args, **kwargs)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/training/input.py", line 1017, in batch
- name=name)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/training/input.py", line 787, in _batch
- dequeued = queue.dequeue_many(batch_size, name=name)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/ops/data_flow_ops.py", line 478, in dequeue_many
- self._queue_ref, n=n, component_types=self._dtypes, name=name)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 3487, in queue_dequeue_many_v2
- component_types=component_types, timeout_ms=timeout_ms, name=name)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
- op_def=op_def)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
- return func(*args, **kwargs)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
- op_def=op_def)
- File "/home/dp92/.local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
- self._traceback = tf_stack.extract_stack()
- OutOfRangeError (see above for traceback): FIFOQueue '_1_input_reader/batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)
- [[node input_reader/batch (defined at /home/dp92/Desktop/deep-stereo/Data_utils/data_reader.py:166) = QueueDequeueManyV2[component_types=[DT_FLOAT, DT_FLOAT, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/device:CPU:0"](input_reader/batch/fifo_queue, input_reader/batch/n)]]
- All Done, Bye Bye!
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement