我是深度学习领域的新宠,并且正在按照该教程来构建自己的自定义模型,该模型可以检测办公室中的其他人:
https://www.youtube.com/watch?v=Rgpfk6eYxJA&t=821s
除了使用CPU训练模型外,我已完成所有步骤。
我的机器的规格是: i7-16GB内存 GPU:3GB的1060ti(GTX)(但在使用GPU时我也遇到相同的OOM错误)
错误日志如下:
2018-08-31 15:12:18.771459: I T:\src\github\tensorflow\tensorflow\core\kernels\data\shuffle_dataset_op.cc:97] Filling up shuffle buffer (this may take a while): 2017 of 2048
2018-08-31 15:12:20.295718: I T:\src\github\tensorflow\tensorflow\core\kernels\data\shuffle_dataset_op.cc:135] Shuffle buffer filled.
2018-08-31 15:12:54.152195: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1275] OP_REQUIRES failed at cast_op.cc:66 : Resource exhausted: OOM when allocating tensor with shape[1,3456,5184,3] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
2018-08-31 15:12:54.152210: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1275] OP_REQUIRES failed at cast_op.cc:66 : Resource exhausted: OOM when allocating tensor with shape[1,3456,5184,3] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
2018-08-31 15:12:54.252864: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1275] OP_REQUIRES failed at cast_op.cc:66 : Resource exhausted: OOM when allocating tensor with shape[1,3456,5184,3] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
2018-08-31 15:12:54.520021: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1275] OP_REQUIRES failed at cast_op.cc:66 : Resource exhausted: OOM when allocating tensor with shape[1,3456,5184,3] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
2018-08-31 15:12:54.796566: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1275] OP_REQUIRES failed at cast_op.cc:66 : Resource exhausted: OOM when allocating tensor with shape[1,3456,5184,3] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
2018-08-31 15:12:55.234806: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1275] OP_REQUIRES failed at cast_op.cc:66 : Resource exhausted: OOM when allocating tensor with shape[1,3456,5184,3] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
2018-08-31 15:12:55.249497: W T:\src\github\tensorflow\tensorflow\core\framework\op_kernel.cc:1275] OP_REQUIRES failed at cast_op.cc:66 : Resource exhausted: OOM when allocating tensor with shape[1,3456,5184,3] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
我为此使用的预训练模型是:faster_rcnn_inception_v2_coco_2018_01_28
配置文件(faster_rcnn_inception_v2_pets.config)为:
# Faster R-CNN with Inception v2, configured for Oxford-IIIT Pets Dataset.
# Users should configure the fine_tune_checkpoint field in the train config as
# well as the label_map_path and input_path fields in the train_input_reader and
# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
# should be configured.
model {
faster_rcnn {
num_classes: 15
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 600
max_dimension: 1024
}
}
feature_extractor {
type: 'faster_rcnn_inception_v2'
first_stage_features_stride: 16
}
first_stage_anchor_generator {
grid_anchor_generator {
scales: [0.25, 0.5, 1.0, 2.0]
aspect_ratios: [0.5, 1.0, 2.0]
height_stride: 16
width_stride: 16
}
}
first_stage_box_predictor_conv_hyperparams {
op: CONV
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
truncated_normal_initializer {
stddev: 0.01
}
}
}
first_stage_nms_score_threshold: 0.0
first_stage_nms_iou_threshold: 0.7
first_stage_max_proposals: 300
first_stage_localization_loss_weight: 2.0
first_stage_objectness_loss_weight: 1.0
initial_crop_size: 14
maxpool_kernel_size: 2
maxpool_stride: 2
second_stage_box_predictor {
mask_rcnn_box_predictor {
use_dropout: false
dropout_keep_probability: 1.0
fc_hyperparams {
op: FC
regularizer {
l2_regularizer {
weight: 0.0
}
}
initializer {
variance_scaling_initializer {
factor: 1.0
uniform: true
mode: FAN_AVG
}
}
}
}
}
second_stage_post_processing {
batch_non_max_suppression {
score_threshold: 0.0
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 300
}
score_converter: SOFTMAX
}
second_stage_localization_loss_weight: 2.0
second_stage_classification_loss_weight: 1.0
}
}
train_config: {
batch_size: 1
optimizer {
momentum_optimizer: {
learning_rate: {
manual_step_learning_rate {
initial_learning_rate: 0.0002
schedule {
step: 900000
learning_rate: .00002
}
schedule {
step: 1200000
learning_rate: .000002
}
}
}
momentum_optimizer_value: 0.9
}
use_moving_average: false
}
gradient_clipping_by_norm: 10.0
fine_tune_checkpoint:
"C:/tensorflow1/models/research/object_detection/faster_rcnn_inception_v2_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: true
load_all_detection_checkpoint_vars: true
# Note: The below line limits the training process to 200K steps, which we
# empirically found to be sufficient enough to train the pets dataset.This
# effectively bypasses the learning rate schedule (the learning rate will
# never decay). Remove the below line to train indefinitely.
num_steps: 200000
data_augmentation_options {
random_horizontal_flip {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "C:/tensorflow1/models/research/object_detection/train.record"
}
label_map_path: "C:/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
}
eval_config: {
metrics_set: "coco_detection_metrics"
num_examples: 3
}
eval_input_reader: {
tf_record_input_reader {
input_path: "C:/tensorflow1/models/research/object_detection/test.record"
}
label_map_path: "C:/tensorflow1/models/research/object_detection/training/labelmap.pbtxt"
shuffle: false
num_readers: 1
}