Open deeprine opened 3 years ago
Can you share the config file and error message as a github gist ? It is hard to read them in github comments.
@vighneshbirodkar
https://gist.github.com/YongSeongLee25/d97e9e5f67d3692ecae81075521102d2
Sorry, I'm giving you a link because I don't know how to upload the code itself to issues.
Hello
The efficient D2 model is being used. I'm going to run the assessment with that code. An error has occurred.
code:
python model_main_tf2.py --model_dir=woo/dev3/Data/train/d2/model_663 --pipeline_config_path=woo/dev3/Data/train/d2/pipeline.config --checkpoint_dir=woo/dev3/Data/train/d2/model_663
error message :
2021-07-30 16:30:04.240837: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 WARNING:tensorflow:Forced number of epochs for all eval validations to be 1. W0730 16:30:05.285229 139928160339776 model_lib_v2.py:1064] Forced number of epochs for all eval validations to be 1. INFO:tensorflow:Maybe overwriting sample_1_of_n_eval_examples: None I0730 16:30:05.285332 139928160339776 config_util.py:552] Maybe overwriting sample_1_of_n_eval_examples: None INFO:tensorflow:Maybe overwriting use_bfloat16: False I0730 16:30:05.285376 139928160339776 config_util.py:552] Maybe overwriting use_bfloat16: False INFO:tensorflow:Maybe overwriting eval_num_epochs: 1 I0730 16:30:05.285417 139928160339776 config_util.py:552] Maybe overwriting eval_num_epochs: 1 WARNING:tensorflow:Expected number of evaluation epochs is 1, but instead encountered
eval_on_train_input_config.num_epochs
= 0. Overwritingnum_epochs
to 1. W0730 16:30:05.285473 139928160339776 model_lib_v2.py:1085] Expected number of evaluation epochs is 1, but instead encounteredeval_on_train_input_config.num_epochs
= 0. Overwritingnum_epochs
to 1. 2021-07-30 16:30:05.291736: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1 2021-07-30 16:30:05.318661: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.318955: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:01:00.0 name: NVIDIA GeForce GTX 1080 Ti computeCapability: 6.1 coreClock: 1.683GHz coreCount: 28 deviceMemorySize: 10.91GiB deviceMemoryBandwidth: 451.17GiB/s 2021-07-30 16:30:05.318972: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2021-07-30 16:30:05.320037: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2021-07-30 16:30:05.321033: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10 2021-07-30 16:30:05.321188: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10 2021-07-30 16:30:05.322310: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10 2021-07-30 16:30:05.322876: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10 2021-07-30 16:30:05.325164: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 2021-07-30 16:30:05.325246: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.325570: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.325832: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0 2021-07-30 16:30:05.326069: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2021-07-30 16:30:05.330362: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 3600000000 Hz 2021-07-30 16:30:05.330595: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55a3e2502090 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2021-07-30 16:30:05.330610: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2021-07-30 16:30:05.378194: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.378557: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55a3e24b1130 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices: 2021-07-30 16:30:05.378574: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): NVIDIA GeForce GTX 1080 Ti, Compute Capability 6.1 2021-07-30 16:30:05.378732: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.379045: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:01:00.0 name: NVIDIA GeForce GTX 1080 Ti computeCapability: 6.1 coreClock: 1.683GHz coreCount: 28 deviceMemorySize: 10.91GiB deviceMemoryBandwidth: 451.17GiB/s 2021-07-30 16:30:05.379067: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2021-07-30 16:30:05.379091: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2021-07-30 16:30:05.379103: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10 2021-07-30 16:30:05.379113: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10 2021-07-30 16:30:05.379122: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10 2021-07-30 16:30:05.379133: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10 2021-07-30 16:30:05.379143: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 2021-07-30 16:30:05.379230: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.379762: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.380020: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0 2021-07-30 16:30:05.380041: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1 2021-07-30 16:30:05.631085: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-07-30 16:30:05.631115: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263] 0 2021-07-30 16:30:05.631121: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0: N 2021-07-30 16:30:05.631271: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.631583: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-07-30 16:30:05.631847: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9230 MB memory) -> physical GPU (device: 0, name: NVIDIA GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1) I0730 16:30:05.719444 139928160339776 ssd_efficientnet_bifpn_feature_extractor.py:143] EfficientDet EfficientNet backbone version: efficientnet-b2 I0730 16:30:05.719544 139928160339776 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet BiFPN num filters: 112 I0730 16:30:05.719586 139928160339776 ssd_efficientnet_bifpn_feature_extractor.py:146] EfficientDet BiFPN num iterations: 5 I0730 16:30:05.725369 139928160339776 efficientnet_model.py:147] round_filter input=32 output=32 I0730 16:30:05.752268 139928160339776 efficientnet_model.py:147] round_filter input=32 output=32 I0730 16:30:05.752362 139928160339776 efficientnet_model.py:147] round_filter input=16 output=16 I0730 16:30:05.851547 139928160339776 efficientnet_model.py:147] round_filter input=16 output=16 I0730 16:30:05.851643 139928160339776 efficientnet_model.py:147] round_filter input=24 output=24 I0730 16:30:06.045676 139928160339776 efficientnet_model.py:147] round_filter input=24 output=24 I0730 16:30:06.045773 139928160339776 efficientnet_model.py:147] round_filter input=40 output=48 I0730 16:30:06.279940 139928160339776 efficientnet_model.py:147] round_filter input=40 output=48 I0730 16:30:06.280038 139928160339776 efficientnet_model.py:147] round_filter input=80 output=88 I0730 16:30:06.544079 139928160339776 efficientnet_model.py:147] round_filter input=80 output=88 I0730 16:30:06.544173 139928160339776 efficientnet_model.py:147] round_filter input=112 output=120 I0730 16:30:06.805504 139928160339776 efficientnet_model.py:147] round_filter input=112 output=120 I0730 16:30:06.805598 139928160339776 efficientnet_model.py:147] round_filter input=192 output=208 I0730 16:30:07.134595 139928160339776 efficientnet_model.py:147] round_filter input=192 output=208 I0730 16:30:07.134699 139928160339776 efficientnet_model.py:147] round_filter input=320 output=352 I0730 16:30:07.263487 139928160339776 efficientnet_model.py:147] round_filter input=1280 output=1408 I0730 16:30:07.290740 139928160339776 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.1, depth_coefficient=1.2, resolution=260, dropout_rate=0.3, blocks=(BlockConfig(input_filters=32, output_filters=16, kernel_size=3, num_repeat=1, expand_ratio=1, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=16, output_filters=24, kernel_size=3, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=24, output_filters=40, kernel_size=5, num_repeat=2, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=40, output_filters=80, kernel_size=3, num_repeat=3, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=80, output_filters=112, kernel_size=5, num_repeat=3, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=112, output_filters=192, kernel_size=5, num_repeat=4, expand_ratio=6, strides=(2, 2), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise'), BlockConfig(input_filters=192, output_filters=320, kernel_size=3, num_repeat=1, expand_ratio=6, strides=(1, 1), se_ratio=0.25, id_skip=True, fused_conv=False, conv_type='depthwise')), stem_base_filters=32, top_base_filters=1280, activation='simple_swish', batch_norm='default', bn_momentum=0.99, bn_epsilon=0.001, weight_decay=5e-06, drop_connect_rate=0.2, depth_divisor=8, min_depth=None, use_se=True, input_channels=3, num_classes=1000, model_name='efficientnet', rescale_input=False, data_format='channels_last', dtype='float32') INFO:tensorflow:Reading unweighted datasets: ['woo/dev3/Data/train/dataset_82.record'] I0730 16:30:07.344820 139928160339776 dataset_builder.py:163] Reading unweighted datasets: ['woo/dev3/Data/train/dataset_82.record'] INFO:tensorflow:Reading record datasets for input file: ['woo/dev3/Data/train/dataset_82.record'] I0730 16:30:07.345714 139928160339776 dataset_builder.py:80] Reading record datasets for input file: ['woo/dev3/Data/train/dataset_82.record'] INFO:tensorflow:Number of filenames to read: 1 I0730 16:30:07.345799 139928160339776 dataset_builder.py:81] Number of filenames to read: 1 WARNING:tensorflow:num_readers has been reduced to 1 to match input file shards. W0730 16:30:07.345847 139928160339776 dataset_builder.py:88] num_readers has been reduced to 1 to match input file shards. WARNING:tensorflow:From /home/leeyongseong/models/학습용/models-master/research/object_detection/builders/dataset_builder.py:105: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated and will be removed in a future vion. Instructions for updating: Usetf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)
instead. If sloppy execution is desired, usetf.data.Options.experimental_deterministic
. W0730 16:30:07.347270 139928160339776 deprecation.py:323] From /home/leeyongseong/models/학습용/models-master/research/object_detection/builders/dataset_builder.py:105: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is depreed and will be removed in a future version. Instructions for updating: Usetf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.experimental.AUTOTUNE)
instead. If sloppy execution is desired, usetf.data.Options.experimental_deterministic
. WARNING:tensorflow:From /home/leeyongseong/models/학습용/models-master/research/object_detection/builders/dataset_builder.py:237: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future veon. Instructions for updating: Usetf.data.Dataset.map() W0730 16:30:07.361915 139928160339776 deprecation.py:323] From /home/leeyongseong/models/학습용/models-master/research/object_detection/builders/dataset_builder.py:237: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecd and will be removed in a future version. Instructions for updating: Use
tf.data.Dataset.map() WARNING:tensorflow:From /home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py:201: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be remove a future version. Instructions for updating: Create atf.sparse.SparseTensor
and usetf.sparse.to_dense
instead. W0730 16:30:09.792060 139928160339776 deprecation.py:323] From /home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py:201: sparse_to_dense (from tensorflow.python.ops.sparss) is deprecated and will be removed in a future version. Instructions for updating: Create atf.sparse.SparseTensor
and usetf.sparse.to_dense
instead. WARNING:tensorflow:From /home/leeyongseong/models/학습용/models-master/research/object_detection/inputs.py:282: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Usetf.cast
instead. W0730 16:30:10.683436 139928160339776 deprecation.py:323] From /home/leeyongseong/models/학습용/models-master/research/object_detection/inputs.py:282: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Usetf.cast
instead. INFO:tensorflow:Waiting for new checkpoint at woo/dev3/Data/train/d2/model_663 I0730 16:30:12.394732 139928160339776 checkpoint_utils.py:125] Waiting for new checkpoint at woo/dev3/Data/train/d2/model_663 INFO:tensorflow:Found new checkpoint at woo/dev3/Data/train/d2/model_663/ckpt-30 I0730 16:30:12.395892 139928160339776 checkpoint_utils.py:134] Found new checkpoint at woo/dev3/Data/train/d2/model_663/ckpt-30 WARNING:tensorflow:From /home/leeyongseong/models/학습용/models-master/research/object_detection/model_lib_v2.py:845: set_learning_phase (from tensorflow.python.keras.backend) is deprecated and will be removed after 2020-10-11. Instructions for updating: Simply pass a True/False value to thetraining
argument of the__call__
method of your layer or model. W0730 16:30:17.353836 139928160339776 deprecation.py:323] From /home/leeyongseong/models/학습용/models-master/research/object_detection/model_lib_v2.py:845: set_learning_phase (from tensorflow.python.keras.backend) is deprecated and will be removed after 2020-11. Instructions for updating: Simply pass a True/False value to thetraining
argument of the__call__
method of your layer or model. 2021-07-30 16:30:34.613273: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10 2021-07-30 16:30:34.713459: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7 WARNING:tensorflow:From /home/leeyongseong/models/학습용/models-master/research/object_detection/eval_util.py:929: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Usetf.cast
instead. W0730 16:30:35.632518 139928160339776 deprecation.py:323] From /home/leeyongseong/models/학습용/models-master/research/object_detection/eval_util.py:929: to_int64 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Usetf.cast
instead. INFO:tensorflow:Finished eval step 0 I0730 16:30:35.637181 139928160339776 model_lib_v2.py:940] Finished eval step 0 WARNING:tensorflow:From /home/leeyongseong/models/학습용/models-master/research/object_detection/utils/visualization_utils.py:617: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a future version. Instructions for updating: tf.py_func is deprecated in TF V2. Instead, there are two options available in V2.tf.py_function
s can use accelerators such as GPUs as well as being differentiable using a gradient tape.W0730 16:30:35.728933 139928160339776 deprecation.py:323] From /home/leeyongseong/models/학습용/models-master/research/object_detection/utils/visualization_utils.py:617: py_func (from tensorflow.python.ops.script_ops) is deprecated and will be removed in a fue version. Instructions for updating: tf.py_func is deprecated in TF V2. Instead, there are two options available in V2.
tf.py_function
s can use accelerators such as GPUs as well as being differentiable using a gradient tape.Traceback (most recent call last): File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/util/nest.py", line 395, in assert_same_structure expand_composites) ValueError: The two structures don't have the same nested structure.
First structure: type=DType str=<dtype: 'uint8'>
Second structure: type=list str=[<tf.Tensor: shape=(600, 600, 3), dtype=uint8, numpy= array([[[254, 254, 254], [254, 254, 254], [254, 254, 254], ..., [254, 254, 254], [254, 254, 254], [254, 254, 254]],
More specifically: Substructure "type=list str=[<tf.Tensor: shape=(600, 600, 3), dtype=uint8, numpy= array([[[254, 254, 254], [254, 254, 254], [254, 254, 254], ..., [254, 254, 254], [254, 254, 254], [254, 254, 254]],
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "model_main_tf2.py", line 113, in
tf.compat.v1.app.run()
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/absl/app.py", line 303, in run
_run_main(main, args)
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/absl/app.py", line 251, in _run_main
sys.exit(main(argv))
File "model_main_tf2.py", line 88, in main
wait_interval=300, timeout=FLAGS.eval_timeout)
File "/home/leeyongseong/models/학습용/models-master/research/object_detection/model_lib_v2.py", line 1139, in eval_continuously
global_step=global_step,
File "/home/leeyongseong/models/학습용/models-master/research/object_detection/model_lib_v2.py", line 950, in eager_eval_loop
keypoint_edges=keypoint_edges or None)
File "/home/leeyongseong/models/학습용/models-master/research/object_detection/utils/visualization_utils.py", line 733, in draw_side_by_side_evaluation_image
use_normalized_coordinates=use_normalized_coordinates)
File "/home/leeyongseong/models/학습용/models-master/research/object_detection/utils/visualization_utils.py", line 621, in draw_bounding_boxes_on_image_tensors
images = tf.map_fn(draw_boxes, elems, dtype=tf.uint8, back_prop=False)
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, *kwargs)
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/ops/map_fn.py", line 499, in map_fn
maximum_iterations=n)
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2735, in while_loop
loop_vars = body(loop_vars)
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2726, in
body = lambda i, lv: (i + 1, orig_body(*lv))
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/ops/map_fn.py", line 484, in compute
nest.assert_same_structure(fn_output_signature or elems, result_value)
File "/home/leeyongseong/다운로드/myanaconda/envs/models-master-20210528T081613Z-001/lib/python3.6/site-packages/tensorflow/python/util/nest.py", line 402, in assert_same_structure
% (str(e), str1, str2))
ValueError: The two structures don't have the same nested structure.
First structure: type=DType str=<dtype: 'uint8'>
Second structure: type=list str=[<tf.Tensor: shape=(600, 600, 3), dtype=uint8, numpy= array([[[254, 254, 254], [254, 254, 254], [254, 254, 254], ..., [254, 254, 254], [254, 254, 254], [254, 254, 254]],
More specifically: Substructure "type=list str=[<tf.Tensor: shape=(600, 600, 3), dtype=uint8, numpy= array([[[254, 254, 254], [254, 254, 254], [254, 254, 254], ..., [254, 254, 254], [254, 254, 254], [254, 254, 254]],
Entire first structure: . Entire second structure: [., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., ., .]
config file :
model { ssd { num_classes: 3 image_resizer { keep_aspect_ratio_resizer { min_dimension: 768 max_dimension: 768 pad_to_max_dimension: true } } feature_extractor { type: "ssd_efficientnet-b2_bifpn_keras" conv_hyperparams { regularizer { l2_regularizer { weight: 3.9999998989515007e-05 } } initializer { truncated_normal_initializer { mean: 0.0 stddev: 0.029999999329447746 } } activation: SWISH batch_norm { decay: 0.9900000095367432 scale: true epsilon: 0.0010000000474974513 } force_use_bias: true } bifpn { min_level: 3 max_level: 7 num_iterations: 5 num_filters: 112 } } box_coder { faster_rcnn_box_coder { y_scale: 1.0 x_scale: 1.0 height_scale: 1.0 width_scale: 1.0 } } matcher { argmax_matcher { matched_threshold: 0.5 unmatched_threshold: 0.5 ignore_thresholds: false negatives_lower_than_unmatched: true force_match_for_each_row: true use_matmul_gather: true } } similarity_calculator { iou_similarity { } } box_predictor { weight_shared_convolutional_box_predictor { conv_hyperparams { regularizer { l2_regularizer { weight: 3.9999998989515007e-05 } } initializer { random_normal_initializer { mean: 0.0 stddev: 0.009999999776482582 } } activation: SWISH batch_norm { decay: 0.9900000095367432 scale: true epsilon: 0.0010000000474974513 } force_use_bias: true } depth: 112 num_layers_before_predictor: 3 kernel_size: 3 class_prediction_bias_init: -4.599999904632568 use_depthwise: true } } anchor_generator { multiscale_anchor_generator { min_level: 3 max_level: 7 anchor_scale: 4.0 aspect_ratios: 1.0 aspect_ratios: 2.0 aspect_ratios: 0.5 scales_per_octave: 3 } } post_processing { batch_non_max_suppression { score_threshold: 9.99999993922529e-09 iou_threshold: 0.5 max_detections_per_class: 100 max_total_detections: 100 } score_converter: SIGMOID } normalize_loss_by_num_matches: true loss { localization_loss { weighted_smooth_l1 { } } classification_loss { weighted_sigmoid_focal { gamma: 1.5 alpha: 0.25 } } classification_weight: 1.0 localization_weight: 1.0 } encode_background_as_zeros: true normalize_loc_loss_by_codesize: true inplace_batchnorm_update: true freeze_batchnorm: false add_background_class: false } } train_config { batch_size: 3 data_augmentation_options { random_horizontal_flip { } } data_augmentation_options { random_scale_crop_and_pad_to_square { output_size: 768 scale_min: 0.10000000149011612 scale_max: 2.0 } } sync_replicas: true optimizer { momentum_optimizer { learning_rate { cosine_decay_learning_rate { learning_rate_base: 0.07999999821186066 total_steps: 150000 warmup_learning_rate: 0.0010000000474974513 warmup_steps: 2500 } } momentum_optimizer_value: 0.8999999761581421 } use_moving_average: false } fine_tune_checkpoint: "" num_steps: 67000 startup_delay_steps: 0.0 replicas_to_aggregate: 8 max_number_of_boxes: 100 unpad_groundtruth_tensors: false fine_tune_checkpoint_type: "classification" use_bfloat16: true fine_tune_checkpoint_version: V2 } train_input_reader: { label_map_path: "woo/dev3/Data/train/label_map_elc.pbtxt" tf_record_input_reader { input_path: "woo/dev3/Data/train/dataset_663.record" } }
eval_config: { metrics_set: "coco_detection_metrics" use_moving_averages: false batch_size: 1; }
eval_input_reader: { label_map_path: "woo/dev3/Data/train/label_map_elc.pbtxt" shuffle: false num_epochs: 1 tf_record_input_reader { input_path: "woo/dev3/Data/train/dataset_82.record" } }
I tried changing the record file, but it didn't work. Is there a way?