SSD目标检测（TensorFlow+pycharm）运行自制数据集，遇坑盘点_5ssdtf.top

前言：最近尝试了下SSD，没看到windows下pycharm版本的教程。遇到各种坑，总结一下。（转载请加链接）
在此先推荐几个不错的博文：https://blog.csdn.net/weixin_39881922/article/details/80569803（源代码从此博文下载）
https://blog.csdn.net/clover_my/article/details/88844697
https://blog.csdn.net/zhangjunp3/article/details/80597312
https://blog.csdn.net/liuyan20062010/article/details/78905517
1.代码文件夹

2.数据集
自制的数据集应放入VOC2007文件夹中，其中包含三个文件夹 Annotations、ImageSets、JPEGImages。Annotations存放.XML标注文件，JPEGImages用于存放数据图片，ImageSets中存放划分的训练集测试集等（意义不大）。
坑1
SSD对数据集的尺寸有要求，所有图片尺寸一定要一样大，(YOLOv3可以多尺寸训练）。之前做过的数据集尺寸不一样，导致标注文件的宽高为0，在做数据转换的时候会报错：ZeroDivisionError。可以用“看图王”软件批量处理尺寸和后缀。

3.tfrecord格式数据转换：
3.1 SSD模型使用的是tfrecord二进制数据，VOC数据集无法直接用于训练，必须先将VOC数据集转换成tfrecord文件。
找到datasets文件夹中pascalvoc_common.py文件，修改你的类别。num_class为你的识别类别数+1



3.2 找到datasets文件夹中pascalvoc_to_tfrecords.py文件，更改文件的83行读取方式为’rb‘；如果你的文件不是.jpg格式，也可以修改图片的类型。其次，修改67行，可以修改几张图片转为一个tfrecords（图中200代表200个数据转为一个tfrecord文件）。


3.3 打开tf_convert_data.py文件，重点设置dataset_dir（即你存放源数据的VOC2007）,output_dir为转化成tfrecord数据后你想保存的位置（我保存在tfrecords_my文件夹中）。设置完成后，点击运行，生成成功。


坑2 报错：ssd-tensorflow报错 labels.append(int(VOC_LABELS[label][0])) KeyError:‘xxx’。解决办法：pascalvoc_to_tfrecords.py文件中103行改为：

4.训练（这个部分坑最多）
4.1 定位到nets文件夹下的ssd_vgg_300.py，修改num_classes和no_annotation_label，均为你的实际类别数+1。

4.2 定位到eval_ssd_network.py，修改num_classes。

4.3 定位到train_ssd_network.py，修改Dataset Flags部分：重点设置 dataset_name、num_classes、dataset_split_name、dataset_dir（tfrecord文件的路径）、model_name、batch_size、max_number_of_steps、checkpoint_path（预训练权重文件的路径）、train_dir（训练后权重文件保存的路径）；
注：checkpoints文件夹下要有vgg_16.ckpt文件，可下载：链接：https://pan.baidu.com/s/1diWbdJdjVbB3AWN99406nA 密码：ge3x

坑3 上述配置完运行应该没问题了，可是还会报错：Process finished with exit code -1073741819(0xC0000005)。解决办法：在run中Edit Configuration配置Parameters（感觉这个操作才是配置参数的过程）:（注意：batch size不可以设置的太大）

python ./train_ssd_network.py  --train_dir=./train_model/  --dataset_dir=./tfrecords_my/  --dataset_name=pascalvoc_2007 --dataset_split_name=train --model_name=ssd_300_vgg   --checkpoint_path=./checkpoints/vgg_16.ckpt   --checkpoint_model_scope=vgg_16 --checkpoint_exclude_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box   --trainable_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box --save_summaries_secs=60   --save_interval_secs=600 --weight_decay=0.0005   --optimizer=adam   --learning_rate=0.001 --learning_rate_decay_factor=0.94   --batch_size=10      --gpu_memory_fraction=0.5
1

注：（1）训练后会每隔一段时间生成一些文件，会占用一部分内存；
（2） 每次训练时如果检测到上次训练保存的文件，程序会接着上一次继续训练。
附上训练的代码：

# Copyright 2016 Paul Balanca. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Generic training script that trains a SSD model using a given dataset."""
import tensorflow as tf
from tensorflow.python.ops import control_flow_ops

from datasets import dataset_factory
from deployment import model_deploy
from nets import nets_factory
from preprocessing import preprocessing_factory
import tf_utils

slim = tf.contrib.slim

DATA_FORMAT = 'NCHW'

# =========================================================================== #
# SSD Network flags.
# =========================================================================== #
tf.app.flags.DEFINE_float(
    'loss_alpha', 1., 'Alpha parameter in the loss function.')
tf.app.flags.DEFINE_float(
    'negative_ratio', 3., 'Negative ratio in the loss function.')
tf.app.flags.DEFINE_float(
    'match_threshold', 0.5, 'Matching threshold in the loss function.')

# =========================================================================== #
# General Flags.
# =========================================================================== #
tf.app.flags.DEFINE_string(
    'train_dir', 'C:/Users/think/Desktop/wp-SSD2/SSD-Tensorflow/log_finetune/',
    'Directory where checkpoints and event logs are written to.')
tf.app.flags.DEFINE_integer('num_clones', 1,
                            'Number of model clones to deploy.')
tf.app.flags.DEFINE_boolean('clone_on_cpu', False,
                            'Use CPUs to deploy clones.')
tf.app.flags.DEFINE_integer(
    'num_readers', 4,
    'The number of parallel readers that read data from the dataset.')
tf.app.flags.DEFINE_integer(
    'num_preprocessing_threads', 4,
    'The number of threads used to create the batches.')

tf.app.flags.DEFINE_integer(
    'log_every_n_steps', 10,
    'The frequency with which logs are print.')
tf.app.flags.DEFINE_integer(
    'save_summaries_secs', 600,
    'The frequency with which summaries are saved, in seconds.')
tf.app.flags.DEFINE_integer(
    'save_interval_secs', 600,
    'The frequency with which the model is saved, in seconds.')
tf.app.flags.DEFINE_float(
    'gpu_memory_fraction', 0.8, 'GPU memory fraction to use.')

# =========================================================================== #
# Optimization Flags.
# =========================================================================== #
tf.app.flags.DEFINE_float(
    'weight_decay', 0.00004, 'The weight decay on the model weights.')
tf.app.flags.DEFINE_string(
    'optimizer', 'rmsprop',
    'The name of the optimizer, one of "adadelta", "adagrad", "adam",'
    '"ftrl", "momentum", "sgd" or "rmsprop".')
tf.app.flags.DEFINE_float(
    'adadelta_rho', 0.95,
    'The decay rate for adadelta.')
tf.app.flags.DEFINE_float(
    'adagrad_initial_accumulator_value', 0.1,
    'Starting value for the AdaGrad accumulators.')
tf.app.flags.DEFINE_float(
    'adam_beta1', 0.9,
    'The exponential decay rate for the 1st moment estimates.')
tf.app.flags.DEFINE_float(
    'adam_beta2', 0.999,
    'The exponential decay rate for the 2nd moment estimates.')
tf.app.flags.DEFINE_float('opt_epsilon', 1.0, 'Epsilon term for the optimizer.')
tf.app.flags.DEFINE_float('ftrl_learning_rate_power', -0.5,
                          'The learning rate power.')
tf.app.flags.DEFINE_float(
    'ftrl_initial_accumulator_value', 0.1,
    'Starting value for the FTRL accumulators.')
tf.app.flags.DEFINE_float(
    'ftrl_l1', 0.0, 'The FTRL l1 regularization strength.')
tf.app.flags.DEFINE_float(
    'ftrl_l2', 0.0, 'The FTRL l2 regularization strength.')
tf.app.flags.DEFINE_float(
    'momentum', 0.9,
    'The momentum for the MomentumOptimizer and RMSPropOptimizer.')
tf.app.flags.DEFINE_float('rmsprop_momentum', 0.9, 'Momentum.')
tf.app.flags.DEFINE_float('rmsprop_decay', 0.9, 'Decay term for RMSProp.')

# =========================================================================== #
# Learning Rate Flags.
# =========================================================================== #
tf.app.flags.DEFINE_string(
    'learning_rate_decay_type',
    'exponential',
    'Specifies how the learning rate is decayed. One of "fixed", "exponential",'
    ' or "polynomial"')
tf.app.flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
tf.app.flags.DEFINE_float(
    'end_learning_rate', 0.001,
    'The minimal end learning rate used by a polynomial decay learning rate.')
tf.app.flags.DEFINE_float(
    'label_smoothing', 0.0, 'The amount of label smoothing.')
tf.app.flags.DEFINE_float(
    'learning_rate_decay_factor', 0.94, 'Learning rate decay factor.')
tf.app.flags.DEFINE_float(
    'num_epochs_per_decay', 2.0,
    'Number of epochs after which learning rate decays.')
tf.app.flags.DEFINE_float(
    'moving_average_decay', None,
    'The decay to use for the moving average.'
    'If left as None, then moving averages are not used.')

# =========================================================================== #
# Dataset Flags.
# =========================================================================== #
tf.app.flags.DEFINE_string(
    'dataset_name', 'pascalvoc_2007', 'The name of the dataset to load.')
tf.app.flags.DEFINE_integer(
    'num_classes', 2, 'Number of classes to use in the dataset.')
tf.app.flags.DEFINE_string(
    'dataset_split_name', 'train', 'The name of the train/test split.')
tf.app.flags.DEFINE_string(
    'dataset_dir', 'C:/Users/think/Desktop/wp-SSD2/SSD-Tensorflow/tfrecords_my/tfrecords_my/', 'The directory where the dataset files are stored.')
tf.app.flags.DEFINE_integer(
    'labels_offset', 0,
    'An offset for the labels in the dataset. This flag is primarily used to '
    'evaluate the VGG and ResNet architectures which do not use a background '
    'class for the ImageNet dataset.')
tf.app.flags.DEFINE_string(
    'model_name', 'ssd_300_vgg', 'The name of the architecture to train.')
tf.app.flags.DEFINE_string(
    'preprocessing_name', None, 'The name of the preprocessing to use. If left '
    'as `None`, then the model_name flag is used.')
tf.app.flags.DEFINE_integer(
    'batch_size', 4, 'The number of samples in each batch.')
tf.app.flags.DEFINE_integer(
    'train_image_size', None, 'Train image size')
tf.app.flags.DEFINE_integer('max_number_of_steps', 50000,
                            'The maximum number of training steps.')

# =========================================================================== #
# Fine-Tuning Flags.
# =========================================================================== #
tf.app.flags.DEFINE_string(
    'checkpoint_path', 'C:/Users/think/Desktop/wp-SSD2/SSD-Tensorflow/checkpoints/ssd_300_vgg.ckpt',
    'The path to a checkpoint from which to fine-tune.')
tf.app.flags.DEFINE_string(
    'checkpoint_model_scope', None,
    'Model scope in the checkpoint. None if the same as the trained model.')
tf.app.flags.DEFINE_string(
    'checkpoint_exclude_scopes', None,
    'Comma-separated list of scopes of variables to exclude when restoring '
    'from a checkpoint.')
tf.app.flags.DEFINE_string(
    'trainable_scopes', None,
    'Comma-separated list of scopes to filter the set of variables to train.'
    'By default, None would train all the variables.')
tf.app.flags.DEFINE_boolean(
    'ignore_missing_vars', False,
    'When restoring a checkpoint would ignore missing variables.')

FLAGS = tf.app.flags.FLAGS


# =========================================================================== #
# Main training routine.
# =========================================================================== #
def main(_):
    if not FLAGS.dataset_dir:
        raise ValueError('You must supply the dataset directory with --dataset_dir')

    tf.logging.set_verbosity(tf.logging.DEBUG)
    with tf.Graph().as_default():
        # Config model_deploy. Keep TF Slim Models structure.
        # Useful if want to need multiple GPUs and/or servers in the future.
        deploy_config = model_deploy.DeploymentConfig(
            num_clones=FLAGS.num_clones,
            clone_on_cpu=FLAGS.clone_on_cpu,
            replica_id=0,
            num_replicas=1,
            num_ps_tasks=0)
        # Create global_step.
        with tf.device(deploy_config.variables_device()):
            global_step = slim.create_global_step()

        # Select the dataset.
        dataset = dataset_factory.get_dataset(
            FLAGS.dataset_name, FLAGS.dataset_split_name, FLAGS.dataset_dir)

        # Get the SSD network and its anchors.
        ssd_class = nets_factory.get_network(FLAGS.model_name)
        ssd_params = ssd_class.default_params._replace(num_classes=FLAGS.num_classes)
        ssd_net = ssd_class(ssd_params)
        ssd_shape = ssd_net.params.img_shape
        ssd_anchors = ssd_net.anchors(ssd_shape)

        # Select the preprocessing function.
        preprocessing_name = FLAGS.preprocessing_name or FLAGS.model_name
        image_preprocessing_fn = preprocessing_factory.get_preprocessing(
            preprocessing_name, is_training=True)

        tf_utils.print_configuration(FLAGS.__flags, ssd_params,
                                     dataset.data_sources, FLAGS.train_dir)
        # =================================================================== #
        # Create a dataset provider and batches.
        # =================================================================== #
        with tf.device(deploy_config.inputs_device()):
            with tf.name_scope(FLAGS.dataset_name + '_data_provider'):
                provider = slim.dataset_data_provider.DatasetDataProvider(
                    dataset,
                    num_readers=FLAGS.num_readers,
                    common_queue_capacity=20 * FLAGS.batch_size,
                    common_queue_min=10 * FLAGS.batch_size,
                    shuffle=True)
            # Get for SSD network: image, labels, bboxes.
            [image, shape, glabels, gbboxes] = provider.get(['image', 'shape',
                                                             'object/label',
                                                             'object/bbox'])
            # Pre-processing image, labels and bboxes.
            image, glabels, gbboxes = \
                image_preprocessing_fn(image, glabels, gbboxes,
                                       out_shape=ssd_shape,
                                       data_format=DATA_FORMAT)
            # Encode groundtruth labels and bboxes.
            gclasses, glocalisations, gscores = \
                ssd_net.bboxes_encode(glabels, gbboxes, ssd_anchors)
            batch_shape = [1] + [len(ssd_anchors)] * 3

            # Training batches and queue.
            r = tf.train.batch(
                tf_utils.reshape_list([image, gclasses, glocalisations, gscores]),
                batch_size=FLAGS.batch_size,
                num_threads=FLAGS.num_preprocessing_threads,
                capacity=5 * FLAGS.batch_size)
            b_image, b_gclasses, b_glocalisations, b_gscores = \
                tf_utils.reshape_list(r, batch_shape)

            # Intermediate queueing: unique batch computation pipeline for all
            # GPUs running the training.
            batch_queue = slim.prefetch_queue.prefetch_queue(
                tf_utils.reshape_list([b_image, b_gclasses, b_glocalisations, b_gscores]),
                capacity=2 * deploy_config.num_clones)

        # =================================================================== #
        # Define the model running on every GPU.
        # =================================================================== #
        def clone_fn(batch_queue):
            """Allows data parallelism by creating multiple
            clones of network_fn."""
            # Dequeue batch.
            b_image, b_gclasses, b_glocalisations, b_gscores = \
                tf_utils.reshape_list(batch_queue.dequeue(), batch_shape)

            # Construct SSD network.
            arg_scope = ssd_net.arg_scope(weight_decay=FLAGS.weight_decay,
                                          data_format=DATA_FORMAT)
            with slim.arg_scope(arg_scope):
                predictions, localisations, logits, end_points = \
                    ssd_net.net(b_image, is_training=True)
            # Add loss function.
            ssd_net.losses(logits, localisations,
                           b_gclasses, b_glocalisations, b_gscores,
                           match_threshold=FLAGS.match_threshold,
                           negative_ratio=FLAGS.negative_ratio,
                           alpha=FLAGS.loss_alpha,
                           label_smoothing=FLAGS.label_smoothing)
            return end_points

        # Gather initial summaries.
        summaries = set(tf.get_collection(tf.GraphKeys.SUMMARIES))

        # =================================================================== #
        # Add summaries from first clone.
        # =================================================================== #
        clones = model_deploy.create_clones(deploy_config, clone_fn, [batch_queue])
        first_clone_scope = deploy_config.clone_scope(0)
        # Gather update_ops from the first clone. These contain, for example,
        # the updates for the batch_norm variables created by network_fn.
        update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS, first_clone_scope)

        # Add summaries for end_points.
        end_points = clones[0].outputs
        for end_point in end_points:
            x = end_points[end_point]
            summaries.add(tf.summary.histogram('activations/' + end_point, x))
            summaries.add(tf.summary.scalar('sparsity/' + end_point,
                                            tf.nn.zero_fraction(x)))
        # Add summaries for losses and extra losses.
        for loss in tf.get_collection(tf.GraphKeys.LOSSES, first_clone_scope):
            summaries.add(tf.summary.scalar(loss.op.name, loss))
        for loss in tf.get_collection('EXTRA_LOSSES', first_clone_scope):
            summaries.add(tf.summary.scalar(loss.op.name, loss))

        # Add summaries for variables.
        for variable in slim.get_model_variables():
            summaries.add(tf.summary.histogram(variable.op.name, variable))

        # =================================================================== #
        # Configure the moving averages.
        # =================================================================== #
        if FLAGS.moving_average_decay:
            moving_average_variables = slim.get_model_variables()
            variable_averages = tf.train.ExponentialMovingAverage(
                FLAGS.moving_average_decay, global_step)
        else:
            moving_average_variables, variable_averages = None, None

        # =================================================================== #
        # Configure the optimization procedure.
        # =================================================================== #
        with tf.device(deploy_config.optimizer_device()):
            learning_rate = tf_utils.configure_learning_rate(FLAGS,
                                                             dataset.num_samples,
                                                             global_step)
            optimizer = tf_utils.configure_optimizer(FLAGS, learning_rate)
            summaries.add(tf.summary.scalar('learning_rate', learning_rate))

        if FLAGS.moving_average_decay:
            # Update ops executed locally by trainer.
            update_ops.append(variable_averages.apply(moving_average_variables))

        # Variables to train.
        variables_to_train = tf_utils.get_variables_to_train(FLAGS)

        # and returns a train_tensor and summary_op
        total_loss, clones_gradients = model_deploy.optimize_clones(
            clones,
            optimizer,
            var_list=variables_to_train)
        # Add total_loss to summary.
        summaries.add(tf.summary.scalar('total_loss', total_loss))

        # Create gradient updates.
        grad_updates = optimizer.apply_gradients(clones_gradients,
                                                 global_step=global_step)
        update_ops.append(grad_updates)
        update_op = tf.group(*update_ops)
        train_tensor = control_flow_ops.with_dependencies([update_op], total_loss,
                                                          name='train_op')

        # Add the summaries from the first clone. These contain the summaries
        summaries |= set(tf.get_collection(tf.GraphKeys.SUMMARIES,
                                           first_clone_scope))
        # Merge all summaries together.
        summary_op = tf.summary.merge(list(summaries), name='summary_op')

        # =================================================================== #
        # Kicks off the training.
        # =================================================================== #
        gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=FLAGS.gpu_memory_fraction)
        config = tf.ConfigProto(log_device_placement=False,
                                gpu_options=gpu_options)
        saver = tf.train.Saver(max_to_keep=5,
                               keep_checkpoint_every_n_hours=1.0,
                               write_version=2,
                               pad_step_number=False)
        slim.learning.train(
            train_tensor,
            logdir=FLAGS.train_dir,
            master='',
            is_chief=True,
            init_fn=tf_utils.get_init_fn(FLAGS),
            summary_op=summary_op,
            number_of_steps=FLAGS.max_number_of_steps,
            log_every_n_steps=FLAGS.log_every_n_steps,
            save_summaries_secs=FLAGS.save_summaries_secs,
            saver=saver,
            save_interval_secs=FLAGS.save_interval_secs,
            session_config=config,
            sync_optimizer=None)


if __name__ == '__main__':
    tf.app.run()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391

5. 检测
定位到demo_test.py。
（1）设置ckpt_filename，即你训练完保存的权重文件的路径。
（2）设置path，即你检测图片的路径。
（3） 设置image_names，即你检测图片的名字。
（4）设置 process_image函数中select_threshold和nms_threshold（参数设置会影响你的检测结果）
坑4 报错：ValueError: Cannot feed value of shape (xxx) for Tensor ‘Placeholder:0’, which has shape ‘(?, ?, xxx)’。解决方法：将源代码中的img = mpimg.imread(path + image_names)改为img=cv2.imread(path+image_names)。
坑5 按上述步骤可以检测了，但是出来的检测图片颜色变了，是因为CV2读取的图像是gbr的图像，需要重新转为rgb图像。即用：
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
大功告成！
附上检测的代码：

#SSD_demo.py 单张图片检测
import os
import math
import random
import time
from PIL import Image, ImageFont, ImageDraw
import numpy as np
import tensorflow as tf
import cv2

slim = tf.contrib.slim

#%matplotlib inline
import matplotlib.pyplot as plt
import matplotlib.image as mpimg

import sys
sys.path.append('../')

from nets import ssd_vgg_300, ssd_common, np_methods
from preprocessing import ssd_vgg_preprocessing
from notebooks import visualization
#import notebooks

# TensorFlow session: grow memory when needed. TF, DO NOT USE ALL MY GPU MEMORY!!!
gpu_options = tf.GPUOptions(allow_growth=True)
config = tf.ConfigProto(log_device_placement=False, gpu_options=gpu_options)
isess = tf.InteractiveSession(config=config)

# Input placeholder.
net_shape = (300, 300)
data_format = 'NHWC'
img_input = tf.placeholder(tf.uint8, shape=(None, None, 3))
# Evaluation pre-processing: resize to SSD net shape.
image_pre, labels_pre, bboxes_pre, bbox_img = ssd_vgg_preprocessing.preprocess_for_eval(
    img_input, None, None, net_shape, data_format, resize=ssd_vgg_preprocessing.Resize.WARP_RESIZE)
image_4d = tf.expand_dims(image_pre, 0)

# Define the SSD model.
reuse = True if 'ssd_net' in locals() else None
ssd_net = ssd_vgg_300.SSDNet()
with slim.arg_scope(ssd_net.arg_scope(data_format=data_format)):
    predictions, localisations, _, _ = ssd_net.net(image_4d, is_training=False, reuse=reuse)

# Restore SSD model.
ckpt_filename = 'C:/Users/think/Desktop/wp-SSD2/SSD-Tensorflow/train_model/model.ckpt-50000'
isess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(isess, ckpt_filename)

# SSD default anchor boxes.
ssd_anchors = ssd_net.anchors(net_shape)

# Main image processing routine.
def process_image(img, select_threshold=xxx, nms_threshold=xxx, net_shape=(300, 300)):
    # Run SSD network.
    rimg, rpredictions, rlocalisations, rbbox_img = isess.run([image_4d, predictions, localisations, bbox_img],
                                                              feed_dict={img_input: img})
    
    # Get classes and bboxes from the net outputs.
    rclasses, rscores, rbboxes = np_methods.ssd_bboxes_select(
            rpredictions, rlocalisations, ssd_anchors,
            select_threshold=select_threshold, img_shape=net_shape, num_classes=21, decode=True)
    
    rbboxes = np_methods.bboxes_clip(rbbox_img, rbboxes)
    rclasses, rscores, rbboxes = np_methods.bboxes_sort(rclasses, rscores, rbboxes, top_k=400)
    rclasses, rscores, rbboxes = np_methods.bboxes_nms(rclasses, rscores, rbboxes, nms_threshold=nms_threshold)
    # Resize bboxes to original image shape. Note: useless for Resize.WARP!
    rbboxes = np_methods.bboxes_resize(rbbox_img, rbboxes)
    return rclasses, rscores, rbboxes
	

#单张图片测试，可视化输出
time1=time.time()
#图片路径
#path = '../demo/test/'
path='C:/Users/think/Desktop/wp-SSD2/SSD-Tensorflow/demo/test/'
#image_names = sorted(os.listdir(path))
image_names ='000003.png'
#img = mpimg.imread(path + image_names)
#img = np.reshape(img, (300, 300,3))

img=cv2.imread(path+image_names)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
rclasses, rscores, rbboxes =  process_image(img)

img_size=img.shape
print(img_size[0],img_size[1])
result={}
for i in range(len(rclasses)):
	midpoint=[0.5*img_size[0]*(rbboxes[i][0]+rbboxes[i][2]),0.5*img_size[1]*(rbboxes[i][1]+rbboxes[i][3])]
	result[i]={rclasses[i]:[rscores[i],midpoint]}

print(result)
print('检测类别为：',rclasses)
print('检测分数为：',rscores)
# visualization.bboxes_draw_on_img(img, rclasses, rscores, rbboxes, visualization.colors_plasma)
visualization.plt_bboxes(img, rclasses, rscores, rbboxes)
time2=time.time()
print('测试时间为：',time2-time1)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100