【发布时间】：2020-06-29 03:01:30
【问题描述】：
说明：
我可以使用 legacy/train.py 训练 fast-rcnn 模型，但是当我尝试使用 model_main.py 以相同的配置设置进行训练时遇到如下问题。 图像分辨率：1920x1080
tensorflow/stream_executor/cuda/cuda_driver.cc:890] failed to alloc 8589934592 bytes on host: CUDA_ERROR_OUT_OF_MEMORY: out of memory
.\tensorflow/core/common_runtime/gpu/gpu_host_allocator.h:44] could not allocate pinned host memory of size: 8589934592
tensorflow/core/common_runtime/bfc_allocator.cc:764] Bin (256): Total Chunks: 4753, Chunks in use: 4753. 1.16MiB allocated for chunks. 1.16MiB in use in bin. 144.3KiB client-requested in use in bin.
tensorflow/core/common_runtime/bfc_allocator.cc:800] InUse at 0000000203800000 next 1 of size 256
我尝试过的：
- 将批量大小设置为 1
- 使用内存增长
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
会话 = tf.Session(config=config)
或
session_config = tf.ConfigProto()
session_config.gpu_options.allow_growth = True
config = tf.estimator.RunConfig(model_dir=FLAGS.model_dir, session_config=session_config, log_step_count_steps=10, save_summary_steps=20, keep_checkpoint_max=20, save_checkpoints_steps=100)
- 不要分配整个 GPU 内存
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.6
会话 = tf.Session(config=config)
或
session_config = tf.ConfigProto()
session_config.gpu_options.per_process_gpu_memory_fraction = 0.6
config = tf.estimator.RunConfig(model_dir=FLAGS.model_dir, session_config=session_config, log_step_count_steps=10, save_summary_steps=20, keep_checkpoint_max=20, save_checkpoints_steps=100)
TensorFlow CUDA_ERROR_OUT_OF_MEMORY
- queue_capacity、min_after_dequeue、num_readers、batch_queue_capacity、num_batch_queue_threads、prefetch_queue_capacity的设置
Out Of Memory when training on Big Images
- 将 min_dimension、max_dimension 降低到 270、480
这些都不适合我。
环境：
- 操作系统平台和发行版：Win 10 专业版：1909
- TensorFlow 安装自：pip tensorflow-gpu
- TensorFlow 1.14 版
- 对象检测：0.1 CUDA/cuDNN 版本：Cuda 10.0、Cudnn 10.0
- GPU 型号和内存：NVIDIA GeForce RTX 2070 SUPER，内存 8 G
- 系统内存：32G
我的配置：
# 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: 2
image_resizer {
keep_aspect_ratio_resizer {
min_dimension: 1080
max_dimension: 1920
}
}
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: ""
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 {
}
}
batch_queue_capacity: 60
num_batch_queue_threads: 30
prefetch_queue_capacity: 40
}
train_input_reader: {
tf_record_input_reader {
input_path: "D:\\object_detection\\train_data\\train.record"
}
label_map_path: "D:\\object_detection\\pascal_label_map.pbtxt"
queue_capacity: 2
min_after_dequeue: 1
num_readers: 1
}
eval_config: {
metrics_set: "coco_detection_metrics"
num_examples: 1101
}
eval_input_reader: {
tf_record_input_reader {
input_path: "D:\\object_detection\\eval_data\\eval.record"
}
label_map_path: "D:\\object_detection\\pascal_label_map.pbtxt"
shuffle: false
num_readers: 1
}
如果有其他解决方案，我将非常感谢您。
【问题讨论】：
标签： tensorflow out-of-memory object-detection object-detection-api faster-rcnn