【发布时间】：2021-02-08 12:40:39
【问题描述】：
对测试数据运行评估我得到以下错误：
TypeError: 'NoneType' object is not iterable
还有这个，可能是什么问题？
INFO:tensorflow:A replica probably exhausted all examples.
Skipping pending examples on other replicas.
这是对测试数据进行评估的代码
!python workspace/model_main_tf2.py \
--pipeline_config_path="/content/models/efficientdet_d4_coco17_tpu-32/pipeline.config" \
--model_dir="/content/models/efficientdet_d4_coco17_tpu-32" \
--checkpoint_dir="/content/models/efficientdet_d4_coco17_tpu-32" \
--alsologtostderr
这里是配置文件：
model {
ssd {
num_classes: 14
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 512
max_dimension: 1024
pad_to_max_dimension: false
}
}
feature_extractor {
type: "ssd_efficientnet-b4_bifpn_keras"
conv_hyperparams {
regularizer {
l2_regularizer {
weight: 4e-05
}
}
initializer {
truncated_normal_initializer {
mean: 0.0
stddev: 0.03
}
}
activation: SWISH
batch_norm {
decay: 0.99
scale: true
epsilon: 0.001
}
force_use_bias: true
}
bifpn {
min_level: 3
max_level: 7
num_iterations: 7
num_filters: 224
}
}
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: 4e-05
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.01
}
}
activation: SWISH
batch_norm {
decay: 0.99
scale: true
epsilon: 0.001
}
force_use_bias: true
}
depth: 224
num_layers_before_predictor: 4
kernel_size: 3
class_prediction_bias_init: -4.6
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: 1e-08
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: 2
data_augmentation_options {
random_horizontal_flip {
}
}
data_augmentation_options {
random_scale_crop_and_pad_to_square {
output_size: 1024
scale_min: 0.1
scale_max: 2.0
}
}
sync_replicas: true
optimizer {
momentum_optimizer {
learning_rate {
cosine_decay_learning_rate {
learning_rate_base: 0.008
total_steps: 300000
warmup_learning_rate: 0.001
warmup_steps: 2500
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
fine_tune_checkpoint: "/content/pretrained_models/efficientdet_d4_coco17_tpu-32/checkpoint/ckpt-0"
num_steps: 5000
startup_delay_steps: 0.0
replicas_to_aggregate: 8
max_number_of_boxes: 100
unpad_groundtruth_tensors: false
fine_tune_checkpoint_type: "detection"
use_bfloat16: false
fine_tune_checkpoint_version: V2
}
train_input_reader {
label_map_path: "/content/LabelsMap.pbtxt"
tf_record_input_reader {
input_path: "/content/annotations/annotations-00024-of-00025"
input_path: "/content/annotations/annotations-00003-of-00025"
input_path: "/content/annotations/annotations-00007-of-00025"
input_path: "/content/annotations/annotations-00019-of-00025"
input_path: "/content/annotations/annotations-00011-of-00025"
input_path: "/content/annotations/annotations-00022-of-00025"
input_path: "/content/annotations/annotations-00023-of-00025"
input_path: "/content/annotations/annotations-00010-of-00025"
input_path: "/content/annotations/annotations-00015-of-00025"
input_path: "/content/annotations/annotations-00014-of-00025"
input_path: "/content/annotations/annotations-00008-of-00025"
input_path: "/content/annotations/annotations-00001-of-00025"
input_path: "/content/annotations/annotations-00004-of-00025"
input_path: "/content/annotations/annotations-00002-of-00025"
input_path: "/content/annotations/annotations-00013-of-00025"
input_path: "/content/annotations/annotations-00017-of-00025"
input_path: "/content/annotations/annotations-00005-of-00025"
input_path: "/content/annotations/annotations-00016-of-00025"
input_path: "/content/annotations/annotations-00000-of-00025"
input_path: "/content/annotations/annotations-00021-of-00025"
input_path: "/content/annotations/annotations-00012-of-00025"
input_path: "/content/annotations/annotations-00006-of-00025"
input_path: "/content/annotations/annotations-00020-of-00025"
}
}
eval_config {
metrics_set: "coco_detection_metrics"
use_moving_averages: false
batch_size: 1
}
eval_input_reader {
label_map_path: "/content/LabelsMap.pbtxt"
shuffle: false
num_epochs: 1
tf_record_input_reader {
input_path: "/content/annotations/annotations-00018-of-00025"
input_path: "/content/annotations/annotations-00009-of-00025"
}
}
这是我运行评估时的完整输出：
2021-02-08 05:25:09.253366: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
WARNING:tensorflow:Forced number of epochs for all eval validations to be 1.
W0208 05:25:12.065460 140012639324032 model_lib_v2.py:1034] Forced number of epochs for all eval validations to be 1.
INFO:tensorflow:Maybe overwriting sample_1_of_n_eval_examples: None
I0208 05:25:12.065674 140012639324032 config_util.py:552] Maybe overwriting sample_1_of_n_eval_examples: None
INFO:tensorflow:Maybe overwriting use_bfloat16: False
I0208 05:25:12.065757 140012639324032 config_util.py:552] Maybe overwriting use_bfloat16: False
INFO:tensorflow:Maybe overwriting eval_num_epochs: 1
I0208 05:25:12.065824 140012639324032 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. Overwriting `num_epochs` to 1.
W0208 05:25:12.065912 140012639324032 model_lib_v2.py:1049] Expected number of evaluation epochs is 1, but instead encountered `eval_on_train_input_config.num_epochs` = 0. Overwriting `num_epochs` to 1.
2021-02-08 05:25:12.076229: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-02-08 05:25:12.078450: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcuda.so.1
2021-02-08 05:25:12.084383: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.085080: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:
pciBusID: 0000:00:04.0 name: Tesla V100-SXM2-16GB computeCapability: 7.0
coreClock: 1.53GHz coreCount: 80 deviceMemorySize: 15.75GiB deviceMemoryBandwidth: 836.37GiB/s
2021-02-08 05:25:12.085116: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
2021-02-08 05:25:12.087591: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.10
2021-02-08 05:25:12.087657: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.10
2021-02-08 05:25:12.090212: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10
2021-02-08 05:25:12.091102: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10
2021-02-08 05:25:12.094218: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10
2021-02-08 05:25:12.095557: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.10
2021-02-08 05:25:12.100331: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.7
2021-02-08 05:25:12.100468: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.101137: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.101764: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0
2021-02-08 05:25:12.102128: 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: AVX512F
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-02-08 05:25:12.102431: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-02-08 05:25:12.102585: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.103196: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1720] Found device 0 with properties:
pciBusID: 0000:00:04.0 name: Tesla V100-SXM2-16GB computeCapability: 7.0
coreClock: 1.53GHz coreCount: 80 deviceMemorySize: 15.75GiB deviceMemoryBandwidth: 836.37GiB/s
2021-02-08 05:25:12.103223: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
2021-02-08 05:25:12.103261: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublas.so.10
2021-02-08 05:25:12.103282: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcublasLt.so.10
2021-02-08 05:25:12.103295: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcufft.so.10
2021-02-08 05:25:12.103313: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcurand.so.10
2021-02-08 05:25:12.103328: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusolver.so.10
2021-02-08 05:25:12.103342: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcusparse.so.10
2021-02-08 05:25:12.103359: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudnn.so.7
2021-02-08 05:25:12.103415: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.104052: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.104613: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1862] Adding visible gpu devices: 0
2021-02-08 05:25:12.104651: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.10.1
2021-02-08 05:25:12.856387: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1261] Device interconnect StreamExecutor with strength 1 edge matrix:
2021-02-08 05:25:12.856446: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1267] 0
2021-02-08 05:25:12.856460: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1280] 0: N
2021-02-08 05:25:12.856682: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.857384: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.858009: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:941] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-02-08 05:25:12.858573: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.
2021-02-08 05:25:12.858621: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1406] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14353 MB memory) -> physical GPU (device: 0, name: Tesla V100-SXM2-16GB, pci bus id: 0000:00:04.0, compute capability: 7.0)
I0208 05:25:12.870367 140012639324032 ssd_efficientnet_bifpn_feature_extractor.py:144] EfficientDet EfficientNet backbone version: efficientnet-b4
I0208 05:25:12.870554 140012639324032 ssd_efficientnet_bifpn_feature_extractor.py:145] EfficientDet BiFPN num filters: 224
I0208 05:25:12.870640 140012639324032 ssd_efficientnet_bifpn_feature_extractor.py:147] EfficientDet BiFPN num iterations: 7
I0208 05:25:12.880502 140012639324032 efficientnet_model.py:147] round_filter input=32 output=48
I0208 05:25:12.909189 140012639324032 efficientnet_model.py:147] round_filter input=32 output=48
I0208 05:25:12.909347 140012639324032 efficientnet_model.py:147] round_filter input=16 output=24
I0208 05:25:13.042321 140012639324032 efficientnet_model.py:147] round_filter input=16 output=24
I0208 05:25:13.042510 140012639324032 efficientnet_model.py:147] round_filter input=24 output=32
I0208 05:25:13.363938 140012639324032 efficientnet_model.py:147] round_filter input=24 output=32
I0208 05:25:13.364143 140012639324032 efficientnet_model.py:147] round_filter input=40 output=56
I0208 05:25:13.683968 140012639324032 efficientnet_model.py:147] round_filter input=40 output=56
I0208 05:25:13.684169 140012639324032 efficientnet_model.py:147] round_filter input=80 output=112
I0208 05:25:14.169368 140012639324032 efficientnet_model.py:147] round_filter input=80 output=112
I0208 05:25:14.169568 140012639324032 efficientnet_model.py:147] round_filter input=112 output=160
I0208 05:25:14.644392 140012639324032 efficientnet_model.py:147] round_filter input=112 output=160
I0208 05:25:14.644582 140012639324032 efficientnet_model.py:147] round_filter input=192 output=272
I0208 05:25:15.287888 140012639324032 efficientnet_model.py:147] round_filter input=192 output=272
I0208 05:25:15.288102 140012639324032 efficientnet_model.py:147] round_filter input=320 output=448
I0208 05:25:15.442380 140012639324032 efficientnet_model.py:147] round_filter input=1280 output=1792
I0208 05:25:15.474397 140012639324032 efficientnet_model.py:458] Building model efficientnet with params ModelConfig(width_coefficient=1.4, depth_coefficient=1.8, resolution=380, dropout_rate=0.4, 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: ['/content/annotations/annotations-00018-of-00025', '/content/annotations/annotations-00009-of-00025']
I0208 05:25:15.696288 140012639324032 dataset_builder.py:163] Reading unweighted datasets: ['/content/annotations/annotations-00018-of-00025', '/content/annotations/annotations-00009-of-00025']
INFO:tensorflow:Reading record datasets for input file: ['/content/annotations/annotations-00018-of-00025', '/content/annotations/annotations-00009-of-00025']
I0208 05:25:15.696582 140012639324032 dataset_builder.py:80] Reading record datasets for input file: ['/content/annotations/annotations-00018-of-00025', '/content/annotations/annotations-00009-of-00025']
INFO:tensorflow:Number of filenames to read: 2
I0208 05:25:15.696693 140012639324032 dataset_builder.py:81] Number of filenames to read: 2
WARNING:tensorflow:num_readers has been reduced to 2 to match input file shards.
W0208 05:25:15.696779 140012639324032 dataset_builder.py:88] num_readers has been reduced to 2 to match input file shards.
WARNING:tensorflow:`shuffle` is false, but the input data stream is still slightly shuffled since `num_readers` > 1.
W0208 05:25:15.697415 140012639324032 dataset_builder.py:94] `shuffle` is false, but the input data stream is still slightly shuffled since `num_readers` > 1.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/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 version.
Instructions for updating:
Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_deterministic`.
W0208 05:25:15.697919 140012639324032 deprecation.py:339] From /usr/local/lib/python3.6/dist-packages/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 version.
Instructions for updating:
Use `tf.data.Dataset.interleave(map_func, cycle_length, block_length, num_parallel_calls=tf.data.AUTOTUNE)` instead. If sloppy execution is desired, use `tf.data.Options.experimental_deterministic`.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/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 version.
Instructions for updating:
Use `tf.data.Dataset.map()
W0208 05:25:15.718755 140012639324032 deprecation.py:339] From /usr/local/lib/python3.6/dist-packages/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 version.
Instructions for updating:
Use `tf.data.Dataset.map()
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Create a `tf.sparse.SparseTensor` and use `tf.sparse.to_dense` instead.
W0208 05:25:19.670241 140012639324032 deprecation.py:339] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201: sparse_to_dense (from tensorflow.python.ops.sparse_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Create a `tf.sparse.SparseTensor` and use `tf.sparse.to_dense` instead.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/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:
Use `tf.cast` instead.
W0208 05:25:21.127015 140012639324032 deprecation.py:339] From /usr/local/lib/python3.6/dist-packages/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:
Use `tf.cast` instead.
INFO:tensorflow:Waiting for new checkpoint at /content/models/efficientdet_d4_coco17_tpu-32
I0208 05:25:23.790350 140012639324032 checkpoint_utils.py:139] Waiting for new checkpoint at /content/models/efficientdet_d4_coco17_tpu-32
INFO:tensorflow:Found new checkpoint at /content/models/efficientdet_d4_coco17_tpu-32/ckpt-6
I0208 05:25:23.791489 140012639324032 checkpoint_utils.py:148] Found new checkpoint at /content/models/efficientdet_d4_coco17_tpu-32/ckpt-6
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:434: UserWarning: `tf.keras.backend.set_learning_phase` is deprecated and will be removed after 2020-10-11. To update it, simply pass a True/False value to the `training` argument of the `__call__` method of your layer or model.
warnings.warn('`tf.keras.backend.set_learning_phase` is deprecated and '
2021-02-08 05:25:31.670912: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2)
2021-02-08 05:25:31.671446: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 2000155000 Hz
INFO:tensorflow:A replica probably exhausted all examples. Skipping pending examples on other replicas.
I0208 05:25:36.730515 140012639324032 model_lib_v2.py:890] A replica probably exhausted all examples. Skipping pending examples on other replicas.
Traceback (most recent call last):
File "workspace/model_main_tf2.py", line 113, in <module>
tf.compat.v1.app.run()
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 300, in run
_run_main(main, args)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 251, in _run_main
sys.exit(main(argv))
File "workspace/model_main_tf2.py", line 88, in main
wait_interval=300, timeout=FLAGS.eval_timeout)
File "/usr/local/lib/python3.6/dist-packages/object_detection/model_lib_v2.py", line 1087, in eval_continuously
global_step=global_step)
File "/usr/local/lib/python3.6/dist-packages/object_detection/model_lib_v2.py", line 956, in eager_eval_loop
for evaluator in evaluators:
TypeError: 'NoneType' object is not iterable
有谁知道问题出在哪里以及如何解决？
【问题讨论】：
-
嗨。你能解决这个问题吗？
标签： python tensorflow object-detection