TF 2 and efficientdet_d7_coco17_tpu-32 instead of _faster_rcnn_inception_v2_pets_
The problem is when i tried to run the training by using:
python` train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/faster_rcnn_inception_v2_pets.config
I GOT THIS ON THE COMMAND PROMPT:
(tensorflow1)` PS C:\tensorflow1\models\research\object_detection> python train.py --logtostderr --train_dir=training/ --pipeline_config_path=training/efficientdet_d7_coco17.config 2020-10-19 16:37:31.809425: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudart64_101.dll WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\absl\app.py:251: main (from __main__) is deprecated and will be removed in a future version. Instructions for updating: Use object_detection/model_main.py. W1019 16:37:34.574319 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\absl\app.py:251: main (from __main__) is deprecated and will be removed in a future version. Instructions for updating: Use object_detection/model_main.py. 2020-10-19 16:37:34.600214: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library nvcuda.dll 2020-10-19 16:37:35.666400: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: pciBusID: 0000:01:00.0 name: Quadro K1000M computeCapability: 3.0 coreClock: 0.8505GHz coreCount: 1 deviceMemorySize: 2.00GiB deviceMemoryBandwidth: 26.82GiB/s 2020-10-19 16:37:35.671684: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudart64_101.dll 2020-10-19 16:37:35.677602: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cublas64_10.dll 2020-10-19 16:37:35.683852: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cufft64_10.dll 2020-10-19 16:37:35.689218: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library curand64_10.dll 2020-10-19 16:37:35.696246: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cusolver64_10.dll 2020-10-19 16:37:35.701566: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cusparse64_10.dll 2020-10-19 16:37:35.706357: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'cudnn64_7.dll'; dlerror: cudnn64_7.dll not found 2020-10-19 16:37:35.709193: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1753] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2020-10-19 16:37:35.726013: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x21873bca9e0 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2020-10-19 16:37:35.729675: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2020-10-19 16:37:35.732603: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix: 2020-10-19 16:37:35.734904: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263] I1019 16:37:35.744936 9100 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet EfficientNet backbone version: efficientnet-b6 I1019 16:37:35.744936 9100 ssd_efficientnet_bifpn_feature_extractor.py:145] EfficientDet BiFPN num filters: 384 I1019 16:37:35.745436 9100 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num iterations: 8 I1019 16:37:35.758453 9100 efficientnet_model.py:148] round_filter input=32 output=56 I1019 16:37:35.802468 9100 efficientnet_model.py:148] round_filter input=32 output=56 I1019 16:37:35.802468 9100 efficientnet_model.py:148] round_filter input=16 output=32 I1019 16:37:36.031706 9100 efficientnet_model.py:148] round_filter input=16 output=32 I1019 16:37:36.032229 9100 efficientnet_model.py:148] round_filter input=24 output=40 I1019 16:37:36.634285 9100 efficientnet_model.py:148] round_filter input=24 output=40 I1019 16:37:36.634285 9100 efficientnet_model.py:148] round_filter input=40 output=72 I1019 16:37:37.298918 9100 efficientnet_model.py:148] round_filter input=40 output=72 I1019 16:37:37.299418 9100 efficientnet_model.py:148] round_filter input=80 output=144 I1019 16:37:38.136620 9100 efficientnet_model.py:148] round_filter input=80 output=144 I1019 16:37:38.136620 9100 efficientnet_model.py:148] round_filter input=112 output=200 I1019 16:37:39.004179 9100 efficientnet_model.py:148] round_filter input=112 output=200 I1019 16:37:39.005179 9100 efficientnet_model.py:148] round_filter input=192 output=344 I1019 16:37:40.433311 9100 efficientnet_model.py:148] round_filter input=192 output=344 I1019 16:37:40.433311 9100 efficientnet_model.py:148] round_filter input=320 output=576 I1019 16:37:40.883462 9100 efficientnet_model.py:148] round_filter input=1280 output=2304 I1019 16:37:40.953514 9100 efficientnet_model.py:462] Building model efficientnet with params ModelConfig(width_coefficient=1.8, depth_coefficient=2.6, resolution=528, dropout_rate=0.5, 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') WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\legacy\trainer.py:265: create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version. Instructions for updating: Please switch to tf.train.create_global_step W1019 16:37:41.120647 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\legacy\trainer.py:265: create_global_step (from tf_slim.ops.variables) is deprecated and will be removed in a future version. Instructions for updating: Please switch to tf.train.create_global_step INFO:tensorflow:Reading unweighted datasets: ['C:/tensorflow1/models/research/object_detection/train.record'] I1019 16:37:41.139898 9100 dataset_builder.py:148] Reading unweighted datasets: ['C:/tensorflow1/models/research/object_detection/train.record'] INFO:tensorflow:Reading record datasets for input file: ['C:/tensorflow1/models/research/object_detection/train.record'] I1019 16:37:41.146900 9100 dataset_builder.py:77] Reading record datasets for input file: ['C:/tensorflow1/models/research/object_detection/train.record'] INFO:tensorflow:Number of filenames to read: 1 I1019 16:37:41.147900 9100 dataset_builder.py:78] Number of filenames to read: 1 WARNING:tensorflow:num_readers has been reduced to 1 to match input file shards. W1019 16:37:41.148901 9100 dataset_builder.py:86] num_readers has been reduced to 1 to match input file shards. WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\builders\dataset_builder.py:103: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated 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. W1019 16:37:41.153904 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\builders\dataset_builder.py:103: parallel_interleave (from tensorflow.python.data.experimental.ops.interleave_ops) is deprecated 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 C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\builders\dataset_builder.py:222: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version. Instructions for updating: Usetf.data.Dataset.map()
W1019 16:37:41.189917 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\builders\dataset_builder.py:222: DatasetV1.map_with_legacy_function (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.data.Dataset.map() WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\builders\dataset_builder.py:48: DatasetV1.make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version. Instructions for updating: This is a deprecated API that should only be used in TF 1 graph mode and legacy TF 2 graph mode available throughtf.compat.v1. In all other situations -- namely, eager mode and insidetf.function-- you can consume dataset elements usingfor elem in dataset: ...or by explicitly creating iterator viaiterator = iter(dataset)and fetching its elements viavalues = next(iterator). Furthermore, this API is not available in TF 2. During the transition from TF 1 to TF 2 you can usetf.compat.v1.data.make_initializable_iterator(dataset)to create a TF 1 graph mode style iterator for a dataset created through TF 2 APIs. Note that this should be a transient state of your code base as there are in general no guarantees about the interoperability of TF 1 and TF 2 code. W1019 16:37:43.031208 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\builders\dataset_builder.py:48: DatasetV1.make_initializable_iterator (from tensorflow.python.data.ops.dataset_ops) is deprecated and will be removed in a future version. Instructions for updating: This is a deprecated API that should only be used in TF 1 graph mode and legacy TF 2 graph mode available throughtf.compat.v1. In all other situations -- namely, eager mode and insidetf.function-- you can consume dataset elements usingfor elem in dataset: ...or by explicitly creating iterator viaiterator = iter(dataset)and fetching its elements viavalues = next(iterator). Furthermore, this API is not available in TF 2. During the transition from TF 1 to TF 2 you can usetf.compat.v1.data.make_initializable_iterator(dataset)to create a TF 1 graph mode style iterator for a dataset created through TF 2 APIs. Note that this should be a transient state of your code base as there are in general no guarantees about the interoperability of TF 1 and TF 2 code. WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\core\batcher.py:101: 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 bytf.data. Usetf.data.Dataset.batch(batch_size)(orpadded_batch(...)ifdynamic_pad=True). W1019 16:37:43.151279 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\core\batcher.py:101: 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 bytf.data. Usetf.data.Dataset.batch(batch_size)(orpadded_batch(...)ifdynamic_pad=True). WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\training\input.py:752: 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 thetf.datamodule. W1019 16:37:43.160428 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\training\input.py:752: 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 thetf.datamodule. WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\training\input.py:752: 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 thetf.datamodule. W1019 16:37:43.163428 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\training\input.py:752: 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 thetf.datamodule. I1019 16:37:43.184436 9100 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet EfficientNet backbone version: efficientnet-b6 I1019 16:37:43.184436 9100 ssd_efficientnet_bifpn_feature_extractor.py:145] EfficientDet BiFPN num filters: 384 I1019 16:37:43.185437 9100 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num iterations: 8 I1019 16:37:43.197441 9100 efficientnet_model.py:148] round_filter input=32 output=56 I1019 16:37:43.254489 9100 efficientnet_model.py:148] round_filter input=32 output=56 I1019 16:37:43.254489 9100 efficientnet_model.py:148] round_filter input=16 output=32 I1019 16:37:43.739614 9100 efficientnet_model.py:148] round_filter input=16 output=32 I1019 16:37:43.739614 9100 efficientnet_model.py:148] round_filter input=24 output=40 I1019 16:37:45.160442 9100 efficientnet_model.py:148] round_filter input=24 output=40 I1019 16:37:45.160942 9100 efficientnet_model.py:148] round_filter input=40 output=72 I1019 16:37:46.483127 9100 efficientnet_model.py:148] round_filter input=40 output=72 I1019 16:37:46.483782 9100 efficientnet_model.py:148] round_filter input=80 output=144 I1019 16:37:48.357353 9100 efficientnet_model.py:148] round_filter input=80 output=144 I1019 16:37:48.357353 9100 efficientnet_model.py:148] round_filter input=112 output=200 I1019 16:37:50.201900 9100 efficientnet_model.py:148] round_filter input=112 output=200 I1019 16:37:50.202400 9100 efficientnet_model.py:148] round_filter input=192 output=344 I1019 16:37:53.021636 9100 efficientnet_model.py:148] round_filter input=192 output=344 I1019 16:37:53.022137 9100 efficientnet_model.py:148] round_filter input=320 output=576 I1019 16:37:53.860046 9100 efficientnet_model.py:148] round_filter input=1280 output=2304 I1019 16:37:53.964131 9100 efficientnet_model.py:462] Building model efficientnet with params ModelConfig(width_coefficient=1.8, depth_coefficient=2.6, resolution=528, dropout_rate=0.5, 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') WARNING:tensorflow:From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\legacy\trainer.py:312: SyncReplicasOptimizer.__init__ (from tensorflow.python.training.sync_replicas_optimizer) is deprecated and will be removed in a future version. Instructions for updating: TheSyncReplicaOptimizerclass is deprecated. For synchronous training, please use [Distribution Strategies](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/distribute). W1019 16:38:16.644356 9100 deprecation.py:323] From C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\legacy\trainer.py:312: SyncReplicasOptimizer.__init__ (from tensorflow.python.training.sync_replicas_optimizer) is deprecated and will be removed in a future version. Instructions for updating: TheSyncReplicaOptimizer` class is deprecated. For synchronous training, please use Distribution Strategies.
INFO:tensorflow:SyncReplicasV2: replicas_to_aggregate=8; total_num_replicas=1
I1019 16:38:16.649864 9100 sync_replicas_optimizer.py:187] SyncReplicasV2: replicas_to_aggregate=8; total_num_replicas=1
Traceback (most recent call last):
File "train.py", line 186, in
tf.app.run()
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\platform\app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\absl\app.py", line 300, in run
_run_main(main, args)
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\absl\app.py", line 251, in _run_main
sys.exit(main(argv))
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\util\deprecation.py", line 324, in new_func
return func(*args, *kwargs)
File "train.py", line 182, in main
graph_hook_fn=graph_rewriter_fn)
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\legacy\trainer.py", line 392, in train
train_config.load_all_detection_checkpoint_vars))
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\meta_architectures\ssd_meta_arch.py", line 1277, in restore_map
return self._feature_extractor.restore_from_classification_checkpoint_fn(
AttributeError: 'SSDEfficientNetB6BiFPNKerasFeatureExtractor' object has no attribute 'restore_from_classification_checkpoint_fn'
ERROR:tensorflow:==================================
Object was never used (type <class 'tensorflow.python.framework.ops.Tensor'>):
<tf.Tensor 'report_uninitialized_variables/boolean_mask/GatherV2:0' shape=(None,) dtype=string>
If you want to mark it as used call its "mark_used()" method.
It was originally created here:
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\util\deprecation.py", line 324, in new_func
return func(args, **kwargs) File "train.py", line 182, in main
graph_hook_fn=graph_rewriter_fn) File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\legacy\trainer.py", line 415, in train
saver=saver) File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\training\sync_replicas_optimizer.py", line 358, in apply_gradients
return train_op File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\util\tf_should_use.py", line 249, in wrapped
error_in_function=error_in_function)
E1019 16:38:50.980139 9100 tf_should_use.py:90] ==================================
Object was never used (type <class 'tensorflow.python.framework.ops.Tensor'>):
<tf.Tensor 'report_uninitialized_variables/boolean_mask/GatherV2:0' shape=(None,) dtype=string>
If you want to mark it as used call its "mark_used()" method.
It was originally created here:
File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\util\deprecation.py", line 324, in new_func
return func(*args, **kwargs) File "train.py", line 182, in main
graph_hook_fn=graph_rewriter_fn) File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\legacy\trainer.py", line 415, in train
saver=saver) File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\training\sync_replicas_optimizer.py", line 358, in apply_gradients
return train_op File "C:\Users\Admin\anaconda3\envs\tensorflow1\lib\site-packages\tensorflow\python\util\tf_should_use.py", line 249, in wrapped
error_in_function=error_in_function)
Is this a error? Please tell me how to fix it.
I tried to replace faster_rcnn_inception_v2_pets.config with efficientdet_d7_coco17.config ( efficientdet_d7_coco17.config is the pipeline.config in efficientdet_d7_coco17_tpu-32, i renamed it) and I also edit some inside efficientdet_d7_coco17.config ,
Jayden0211
commented
3 years ago
### Help me plz,...
I am following this: [https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10] But instead of using TF 1, I use:
Is this a error? Please tell me how to fix it.
THEY ARE:
fine_tune_checkpoint: "C:\tensorflow1\models\research\object_detection\efficientdet_d7_coco17_tpu- 32\checkpoint\ckpt-0.ckpt"
label_map_path: "C:/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
input_path: "C:/tensorflow1/models/research/object_detection/train.record"
-label_map_path: "C:/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
-input_path: "C:/tensorflow1/models/research/object_detection/test.record"
Plz help me, i can't find the answer Love