Problem with using pretrained model (superpoint-coco) for detections. Key magicpoint/detector/conv1/bn/beta not found in checkpoint [[{{node save/RestoreV2}}]]

Hi @rpautrat,

I am trying to use the pre-trained model for detection (sp-v6). !CUDA_VISIBLE_DEVICES=0 python export_detections.py configs/magic-point_coco_export.yaml sp_v6 --pred_only --batch_size=1 --export_name=sp_coco_calib And I got the following error message.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) /usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) /usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) /usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) /usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) /usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /usr/local/lib/python3.6/dist-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) [06/01/2022 14:35:52 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/experiment.py:57: The name tf.set_random_seed is deprecated. Please use tf.compat.v1.set_random_seed instead.

[06/01/2022 14:35:52 INFO] Number of GPUs detected: 1 base_path: /content/drive/MyDrive/SuperPoint/superpoint/data/Images [06/01/2022 14:35:52 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/datasets/coco.py:70: The name tf.read_file is deprecated. Please use tf.io.read_file instead.

[06/01/2022 14:35:52 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/datasets/utils/pipeline.py:96: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. [06/01/2022 14:35:52 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/datasets/utils/pipeline.py:98: The name tf.image.resize_images is deprecated. Please use tf.image.resize instead.

[06/01/2022 14:35:52 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/datasets/utils/pipeline.py:98: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. [06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/datasets/utils/pipeline.py:100: The name tf.image.resize_image_with_crop_or_pad is deprecated. Please use tf.image.resize_with_crop_or_pad instead.

[06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/datasets/base_dataset.py:109: DatasetV1.make_one_shot_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version. Instructions for updating: Use for ... in dataset: to iterate over a dataset. If using tf.estimator, return the Dataset object directly from your input function. As a last resort, you can use tf.compat.v1.data.make_one_shot_iterator(dataset). [06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/datasets/base_dataset.py:111: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.

2022-06-01 14:35:53.560869: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcuda.so.1 2022-06-01 14:35:53.592251: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.592864: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties: name: Tesla T4 major: 7 minor: 5 memoryClockRate(GHz): 1.59 pciBusID: 0000:00:04.0 2022-06-01 14:35:53.593143: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0 2022-06-01 14:35:53.594574: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0 2022-06-01 14:35:53.595759: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0 2022-06-01 14:35:53.596134: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0 2022-06-01 14:35:53.597902: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0 2022-06-01 14:35:53.599135: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0 2022-06-01 14:35:53.603124: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7 2022-06-01 14:35:53.603227: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.604120: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.604676: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0 2022-06-01 14:35:53.605022: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2022-06-01 14:35:53.808272: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.808998: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3098fc0 executing computations on platform CUDA. Devices: 2022-06-01 14:35:53.809032: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Tesla T4, Compute Capability 7.5 2022-06-01 14:35:53.810680: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2199995000 Hz 2022-06-01 14:35:53.810981: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x30996c0 executing computations on platform Host. Devices: 2022-06-01 14:35:53.811026: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): , 2022-06-01 14:35:53.811180: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.811709: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties: name: Tesla T4 major: 7 minor: 5 memoryClockRate(GHz): 1.59 pciBusID: 0000:00:04.0 2022-06-01 14:35:53.811771: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0 2022-06-01 14:35:53.811794: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0 2022-06-01 14:35:53.811813: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0 2022-06-01 14:35:53.811832: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0 2022-06-01 14:35:53.811864: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0 2022-06-01 14:35:53.811882: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0 2022-06-01 14:35:53.811902: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7 2022-06-01 14:35:53.811963: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.812502: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.813003: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0 2022-06-01 14:35:53.813071: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0 2022-06-01 14:35:53.814014: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-06-01 14:35:53.814037: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0 2022-06-01 14:35:53.814047: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N 2022-06-01 14:35:53.814143: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.814745: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:53.815324: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:40] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0. 2022-06-01 14:35:53.815365: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14257 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:04.0, compute capability: 7.5) [06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py:105: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

[06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py:121: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

[06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py:153: The name tf.train.replica_device_setter is deprecated. Please use tf.compat.v1.train.replica_device_setter instead.

[06/01/2022 14:35:53 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/backbones/vgg.py:10: conv2d (from tensorflow.python.layers.convolutional) is deprecated and will be removed in a future version. Instructions for updating: Use tf.keras.layers.Conv2D instead. [06/01/2022 14:35:53 WARNING] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:1251: calling VarianceScaling.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version. Instructions for updating: Call initializer instance with the dtype argument instead of passing it to the constructor [06/01/2022 14:35:53 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe61f029b0>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe61f029b0>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:53 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/backbones/vgg.py:14: batch_normalization (from tensorflow.python.layers.normalization) is deprecated and will be removed in a future version. Instructions for updating: Use keras.layers.BatchNormalization instead. In particular, tf.control_dependencies(tf.GraphKeys.UPDATE_OPS) should not be used (consult the tf.keras.layers.batch_normalization documentation). [06/01/2022 14:35:53 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe61f029b0>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe61f029b0>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:53 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe61f02cf8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe61f02cf8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe61f02cf8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe61f02cf8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/backbones/vgg.py:28: max_pooling2d (from tensorflow.python.layers.pooling) is deprecated and will be removed in a future version. Instructions for updating: Use keras.layers.MaxPooling2D instead. [06/01/2022 14:35:54 WARNING] Entity <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe61f47518>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe61f47518>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503c5e80>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503c5e80>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50425278>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50425278>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbedf7d7b38>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbedf7d7b38>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbedf7d7b38>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbedf7d7b38>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe61f47518>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe61f47518>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe61f47518>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe61f47518>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe50457b00>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe50457b00>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50457b00>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50457b00>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe61f02c88>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe61f02c88>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503da630>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503da630>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:54 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:54 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503ce828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:55 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123b90b8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123b90b8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe123b90b8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe123b90b8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:55 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123b9080>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123b9080>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe123b9080>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe123b9080>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 WARNING] Entity <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe1241edd8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe1241edd8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:55 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123b9ba8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123b9ba8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50457908>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50457908>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:55 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe50457908>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe50457908>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50457908>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe50457908>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 WARNING] Entity <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe1241edd8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe1241edd8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:55 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:56 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe501d0400>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe501d0400>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe501d0400>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe501d0400>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:56 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe12355198>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe12355198>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe12355198>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe12355198>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] Entity <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe1241edd8>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Pooling2D.call of <tensorflow.python.layers.pooling.MaxPooling2D object at 0x7fbe1241edd8>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:56 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe502f3828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe502f3828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe502f3828>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe502f3828>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:56 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503dab70>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503dab70>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503a92b0>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503a92b0>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:56 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123c5278>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe123c5278>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe1237ab38>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe1237ab38>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 INFO] Scale of 0 disables regularizer. [06/01/2022 14:35:56 WARNING] Entity <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503a92b0>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method Conv.call of <tensorflow.python.layers.convolutional.Conv2D object at 0x7fbe503a92b0>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] Entity <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503a92b0>> could not be transformed and will be executed as-is. Please report this to the AutgoGraph team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10) and attach the full output. Cause: converting <bound method BatchNormalization.call of <tensorflow.python.layers.normalization.BatchNormalization object at 0x7fbe503a92b0>>: AttributeError: module 'gast' has no attribute 'Str' [06/01/2022 14:35:56 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/utils.py:179: add_dispatch_support..wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.where in 2.0, which has the same broadcast rule as np.where 2022-06-01 14:35:56.671165: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:56.671799: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties: name: Tesla T4 major: 7 minor: 5 memoryClockRate(GHz): 1.59 pciBusID: 0000:00:04.0 2022-06-01 14:35:56.671925: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudart.so.10.0 2022-06-01 14:35:56.671953: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0 2022-06-01 14:35:56.671975: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcufft.so.10.0 2022-06-01 14:35:56.671995: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcurand.so.10.0 2022-06-01 14:35:56.672015: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusolver.so.10.0 2022-06-01 14:35:56.672035: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcusparse.so.10.0 2022-06-01 14:35:56.672055: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7 2022-06-01 14:35:56.672140: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:56.672713: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:56.673226: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0 2022-06-01 14:35:56.673263: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix: 2022-06-01 14:35:56.673277: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0 2022-06-01 14:35:56.673287: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N 2022-06-01 14:35:56.673374: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:56.673919: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1005] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2022-06-01 14:35:56.674423: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14257 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:04.0, compute capability: 7.5) 2022-06-01 14:35:56.784447: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. [06/01/2022 14:35:56 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py:392: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.

[06/01/2022 14:35:56 WARNING] From /content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py:393: The name tf.gfile.IsDirectory is deprecated. Please use tf.io.gfile.isdir instead.

[06/01/2022 14:35:57 WARNING] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version. Instructions for updating: Use standard file APIs to check for files with this prefix. [06/01/2022 14:35:57 INFO] Restoring parameters from /content/drive/MyDrive/SuperPoint/superpoint/runs/sp_v6/model.ckpt-300000 2022-06-01 14:35:58.408293: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at save_restore_v2_ops.cc:184 : Not found: Key magicpoint/detector/conv1/bn/beta not found in checkpoint Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1356, in _do_call return fn(*args) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1341, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1429, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.NotFoundError: Key magicpoint/detector/conv1/bn/beta not found in checkpoint [[{{node save/RestoreV2}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 1286, in restore {self.saver_def.filename_tensor_name: save_path}) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 950, in run run_metadata_ptr) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1173, in _run feed_dict_tensor, options, run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1350, in _do_run run_metadata) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1370, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.NotFoundError: Key magicpoint/detector/conv1/bn/beta not found in checkpoint [[node save/RestoreV2 (defined at /content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py:392) ]]

Original stack trace for 'save/RestoreV2': File "export_detections.py", line 40, in net.load(str(checkpoint)) File "/content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py", line 392, in load saver = tf.train.Saver(save_relative_paths=True) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 825, in init self.build() File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 837, in build self._build(self._filename, build_save=True, build_restore=True) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 875, in _build build_restore=build_restore) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 508, in _build_internal restore_sequentially, reshape) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 328, in _AddRestoreOps restore_sequentially) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 575, in bulk_restore return io_ops.restore_v2(filename_tensor, names, slices, dtypes) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_io_ops.py", line 1696, in restore_v2 name=name) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper op_def=op_def) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func return func(*args, **kwargs) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 3616, in create_op op_def=op_def) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 2005, in init self._traceback = tf_stack.extract_stack()

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 1296, in restore names_to_keys = object_graph_key_mapping(save_path) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 1614, in object_graph_key_mapping object_graph_string = reader.get_tensor(trackable.OBJECT_GRAPH_PROTO_KEY) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/pywrap_tensorflow_internal.py", line 678, in get_tensor return CheckpointReader_GetTensor(self, compat.as_bytes(tensor_str)) tensorflow.python.framework.errors_impl.NotFoundError: Key _CHECKPOINTABLE_OBJECT_GRAPH not found in checkpoint

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "export_detections.py", line 40, in net.load(str(checkpoint)) File "/content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py", line 397, in load saver.restore(self.sess, checkpoint_path) File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/saver.py", line 1302, in restore err, "a Variable name or other graph key that is missing") tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Key magicpoint/detector/conv1/bn/beta not found in checkpoint [[node save/RestoreV2 (defined at /content/drive/MyDrive/SuperPoint/superpoint/models/base_model.py:392) ]]

I have tried the other two pre-trained models and they had no problem with detections.

rpautrat / SuperPoint

Problem with using pretrained model (superpoint-coco) for detections. Key magicpoint/detector/conv1/bn/beta not found in checkpoint [[{{node save/RestoreV2}}]] #258