Tensorflow:是否需要为较大的输入图像修改图像大小调整参数?
Tensorflow: Do Image Resizing parameters need to be modified for larger input images?
我正在使用 200 张训练图像和 40 张测试图像训练图像识别算法(TesorFlow 1.15,Python 3.7.7)。每张图片的尺寸为 4000 x 3000 像素,因此它们都非常大。我正在训练以下算法(SSD Mobilenet V1):
model {
ssd {
num_classes: 1
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
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
}
}
similarity_calculator {
iou_similarity {
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.95
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.3333
}
}
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
box_predictor {
convolutional_box_predictor {
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 1
box_code_size: 4
apply_sigmoid_to_scores: false
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
}
feature_extractor {
type: 'ssd_mobilenet_v1'
min_depth: 16
depth_multiplier: 1.0
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
loss {
classification_loss {
weighted_sigmoid {
}
}
localization_loss {
weighted_smooth_l1 {
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 3
optimizer {
rms_prop_optimizer: {
learning_rate: {
exponential_decay_learning_rate {
initial_learning_rate: 0.004
decay_steps: 800720
decay_factor: 0.95
}
}
momentum_optimizer_value: 0.9
decay: 0.9
epsilon: 1.0
}
}
fine_tune_checkpoint: "ssd_mobilenet_v1_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: 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 {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "data/train.record"
}
label_map_path: "data/object-detection.pbtxt"
}
eval_config: {
num_examples: 40
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader: {
tf_record_input_reader {
input_path: "data/test.record"
}
label_map_path: "training/object-detection.pbtxt"
shuffle: false
num_readers: 1
}
修改后的类包括:
- num_classes: 1(匹配 类 我正在尝试训练算法检测的数量)
- batch_size = 3
- Train/test 路径目录
- eval_config: {num_examples: 40 #匹配我测试文件夹中的测试图像数量
我不希望缩小图像尺寸,因为我有很多标记数据超出了以下范围:
fixed_shape_resizer {
height: 300
width: 300
维度。 我需要消除这个吗?我是 TensorFlow 的新手,对这些事情没有太多经验,所以任何信息都会有所帮助。
首先,SSD需要固定形状(宽度与高度相同)。这是因为其配置为具有 fully connected layers.
的神经网络
所以你无论如何都要调整大小。但我明白为什么你不想因为信息丢失而调整太多。我认为理论上可以在如此大的图像上进行训练,但实际上并非如此。训练分批获取图像并将它们加载到内存中。使用这样的大小,您可能 运行 内存不足。除此之外,训练时间也会更长。
这就是经常使用调整大小的原因。所以有两种可能的方法。调整到更小的尺寸(当然你可以尝试大于 300x300,但大于 640x640 不太现实)。但是你也可以将每张图像分成例如 4 张图像,你可以在这些图像上训练模型。这样,您丢失的信息就会减少。但由于数据集较大,因此需要更多时间进行训练,这在某些方面也有好处。这可能是最好的方法。
我正在使用 200 张训练图像和 40 张测试图像训练图像识别算法(TesorFlow 1.15,Python 3.7.7)。每张图片的尺寸为 4000 x 3000 像素,因此它们都非常大。我正在训练以下算法(SSD Mobilenet V1):
model {
ssd {
num_classes: 1
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}
}
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
}
}
similarity_calculator {
iou_similarity {
}
}
anchor_generator {
ssd_anchor_generator {
num_layers: 6
min_scale: 0.2
max_scale: 0.95
aspect_ratios: 1.0
aspect_ratios: 2.0
aspect_ratios: 0.5
aspect_ratios: 3.0
aspect_ratios: 0.3333
}
}
image_resizer {
fixed_shape_resizer {
height: 300
width: 300
}
}
box_predictor {
convolutional_box_predictor {
min_depth: 0
max_depth: 0
num_layers_before_predictor: 0
use_dropout: false
dropout_keep_probability: 0.8
kernel_size: 1
box_code_size: 4
apply_sigmoid_to_scores: false
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
}
feature_extractor {
type: 'ssd_mobilenet_v1'
min_depth: 16
depth_multiplier: 1.0
conv_hyperparams {
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.00004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
train: true,
scale: true,
center: true,
decay: 0.9997,
epsilon: 0.001,
}
}
}
loss {
classification_loss {
weighted_sigmoid {
}
}
localization_loss {
weighted_smooth_l1 {
}
}
hard_example_miner {
num_hard_examples: 3000
iou_threshold: 0.99
loss_type: CLASSIFICATION
max_negatives_per_positive: 3
min_negatives_per_image: 0
}
classification_weight: 1.0
localization_weight: 1.0
}
normalize_loss_by_num_matches: true
post_processing {
batch_non_max_suppression {
score_threshold: 1e-8
iou_threshold: 0.6
max_detections_per_class: 100
max_total_detections: 100
}
score_converter: SIGMOID
}
}
}
train_config: {
batch_size: 3
optimizer {
rms_prop_optimizer: {
learning_rate: {
exponential_decay_learning_rate {
initial_learning_rate: 0.004
decay_steps: 800720
decay_factor: 0.95
}
}
momentum_optimizer_value: 0.9
decay: 0.9
epsilon: 1.0
}
}
fine_tune_checkpoint: "ssd_mobilenet_v1_coco_2018_01_28/model.ckpt"
from_detection_checkpoint: 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 {
}
}
data_augmentation_options {
ssd_random_crop {
}
}
}
train_input_reader: {
tf_record_input_reader {
input_path: "data/train.record"
}
label_map_path: "data/object-detection.pbtxt"
}
eval_config: {
num_examples: 40
# Note: The below line limits the evaluation process to 10 evaluations.
# Remove the below line to evaluate indefinitely.
max_evals: 10
}
eval_input_reader: {
tf_record_input_reader {
input_path: "data/test.record"
}
label_map_path: "training/object-detection.pbtxt"
shuffle: false
num_readers: 1
}
修改后的类包括:
- num_classes: 1(匹配 类 我正在尝试训练算法检测的数量)
- batch_size = 3
- Train/test 路径目录
- eval_config: {num_examples: 40 #匹配我测试文件夹中的测试图像数量
我不希望缩小图像尺寸,因为我有很多标记数据超出了以下范围:
fixed_shape_resizer {
height: 300
width: 300
维度。 我需要消除这个吗?我是 TensorFlow 的新手,对这些事情没有太多经验,所以任何信息都会有所帮助。
首先,SSD需要固定形状(宽度与高度相同)。这是因为其配置为具有 fully connected layers.
的神经网络所以你无论如何都要调整大小。但我明白为什么你不想因为信息丢失而调整太多。我认为理论上可以在如此大的图像上进行训练,但实际上并非如此。训练分批获取图像并将它们加载到内存中。使用这样的大小,您可能 运行 内存不足。除此之外,训练时间也会更长。
这就是经常使用调整大小的原因。所以有两种可能的方法。调整到更小的尺寸(当然你可以尝试大于 300x300,但大于 640x640 不太现实)。但是你也可以将每张图像分成例如 4 张图像,你可以在这些图像上训练模型。这样,您丢失的信息就会减少。但由于数据集较大,因此需要更多时间进行训练,这在某些方面也有好处。这可能是最好的方法。