SSD

4-Object_Detection/SSD/core/backbone.py

@@ -0,0 +1,50 @@
+#! /usr/bin/env python
+# coding=utf-8
+#================================================================
+#   Copyright (C) 2019 * Ltd. All rights reserved.
+#
+#   Editor      : VIM
+#   File name   : backbone.py
+#   Author      : YunYang1994
+#   Created date: 2019-07-11 23:37:51
+#   Description :
+#
+#================================================================
+
+import tensorflow as tf
+
+def vgg16(input_data):
+
+#======================================VGG16_start===================================================
+    # conv1
+    conv = tf.keras.layers.Conv2D(64, 3, activation='relu', padding='same')(input_data) #conv1_1
+    conv = tf.keras.layers.Conv2D(64, 3, activation='relu', padding='same')(conv) #conv1_2
+    conv   = tf.keras.layers.MaxPooling2D(2, strides=2, padding='same')(conv) #pool1
+
+    # conv2
+    conv = tf.keras.layers.Conv2D(128, 3, activation='relu', padding='same')(conv)#conv2_1
+    conv = tf.keras.layers.Conv2D(128, 3, activation='relu', padding='same')(conv)#conv2_2
+    conv = tf.keras.layers.MaxPooling2D(2, strides=2, padding='same')(conv)#pool2
+
+    # conv3
+    conv = tf.keras.layers.Conv2D(256, 3, activation='relu', padding='same')(conv)#conv3_1
+    conv = tf.keras.layers.Conv2D(256, 3, activation='relu', padding='same')(conv)#conv3_2
+    conv = tf.keras.layers.Conv2D(256, 3, activation='relu', padding='same')(conv)#conv3_3
+    conv   = tf.keras.layers.MaxPooling2D(2, strides=2, padding='same')(conv)#pool3
+
+    # conv4
+    conv = tf.keras.layers.Conv2D(512, 3, activation='relu', padding='same')(conv)
+    conv = tf.keras.layers.Conv2D(512, 3, activation='relu', padding='same')(conv)
+    conv = tf.keras.layers.Conv2D(512, 3, activation='relu', padding='same')(conv)
+    conv4 = conv
+    conv = tf.keras.layers.MaxPooling2D(2, strides=2, padding='same')(conv)
+
+    # conv5
+    conv = tf.keras.layers.Conv2D(512, 3, activation='relu', padding='same')(conv)
+    conv = tf.keras.layers.Conv2D(512, 3, activation='relu', padding='same')(conv)
+    conv = tf.keras.layers.Conv2D(512, 3, activation='relu', padding='same')(conv)
+    conv = tf.keras.layers.MaxPooling2D(3, strides=1, padding='same')(conv)
+
+    return conv4, conv
+
+

4-Object_Detection/SSD/core/common.py

@@ -0,0 +1,58 @@
+#! /usr/bin/env python
+# coding=utf-8
+#================================================================
+#   Copyright (C) 2019 * Ltd. All rights reserved.
+#
+#   Editor      : VIM
+#   File name   : common.py
+#   Author      : YunYang1994
+#   Created date: 2019-07-11 23:12:53
+#   Description :
+#
+#================================================================
+
+import tensorflow as tf
+
+class BatchNormalization(tf.keras.layers.BatchNormalization):
+    """
+    "Frozen state" and "inference mode" are two separate concepts.
+    `layer.trainable = False` is to freeze the layer, so the layer will use
+    stored moving `var` and `mean` in the "inference mode", and both `gama`
+    and `beta` will not be updated !
+    """
+    def call(self, x, training=False):
+        if not training:
+            training = tf.constant(False)
+        training = tf.logical_and(training, self.trainable)
+        return super().call(x, training)
+
+def convolutional(input_layer, filters_shape, downsample=False, activate=True, bn=True):
+    if downsample:
+        input_layer = tf.keras.layers.ZeroPadding2D(((1, 0), (1, 0)))(input_layer)
+        padding = 'valid'
+        strides = 2
+    else:
+        strides = 1
+        padding = 'same'
+
+    conv = tf.keras.layers.Conv2D(filters=filters_shape[-1], kernel_size = filters_shape[0], strides=strides, padding=padding,
+                                  use_bias=not bn, kernel_regularizer=tf.keras.regularizers.l2(0.0005),
+                                  kernel_initializer=tf.random_normal_initializer(stddev=0.01),
+                                  bias_initializer=tf.constant_initializer(0.))(input_layer)
+
+    if bn: conv = BatchNormalization()(conv)
+    if activate == True: conv = tf.nn.leaky_relu(conv, alpha=0.1)
+
+    return conv
+
+def residual_block(input_layer, input_channel, filter_num1, filter_num2):
+    short_cut = input_layer
+    conv = convolutional(input_layer, filters_shape=(1, 1, input_channel, filter_num1))
+    conv = convolutional(conv       , filters_shape=(3, 3, filter_num1,   filter_num2))
+
+    residual_output = short_cut + conv
+    return residual_output
+
+def upsample(input_layer):
+    return tf.image.resize(input_layer, (input_layer.shape[1] * 2, input_layer.shape[2] * 2), method='nearest')
+

4-Object_Detection/SSD/core/config.py

@@ -0,0 +1,58 @@
+#! /usr/bin/env python
+# coding=utf-8
+#================================================================
+#   Copyright (C) 2019 * Ltd. All rights reserved.
+#
+#   Editor      : VIM
+#   File name   : config.py
+#   Author      : YunYang1994
+#   Created date: 2019-02-28 13:06:54
+#   Description :
+#
+#================================================================
+
+from easydict import EasyDict as edict
+
+
+__C                           = edict()
+# Consumers can get config by: from config import cfg
+
+cfg                           = __C
+
+# YOLO options
+__C.YOLO                      = edict()
+
+# Set the class name
+__C.YOLO.CLASSES              = "./data/classes/coco.names"
+__C.YOLO.ANCHORS              = "./data/anchors/basline_anchors.txt"
+__C.YOLO.STRIDES              = [8, 16, 32]
+__C.YOLO.ANCHOR_PER_SCALE     = 3
+__C.YOLO.IOU_LOSS_THRESH      = 0.5
+
+# Train options
+__C.TRAIN                     = edict()
+
+__C.TRAIN.ANNOT_PATH          = "./data/dataset/yymnist_train.txt"
+__C.TRAIN.BATCH_SIZE          = 4
+# __C.TRAIN.INPUT_SIZE            = [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
+__C.TRAIN.INPUT_SIZE          = [416]
+__C.TRAIN.DATA_AUG            = True
+__C.TRAIN.LR_INIT             = 1e-3
+__C.TRAIN.LR_END              = 1e-6
+__C.TRAIN.WARMUP_EPOCHS       = 2
+__C.TRAIN.EPOCHS              = 30
+
+
+
+# TEST options
+__C.TEST                      = edict()
+
+__C.TEST.ANNOT_PATH           = "./data/dataset/yymnist_test.txt"
+__C.TEST.BATCH_SIZE           = 2
+__C.TEST.INPUT_SIZE           = 544
+__C.TEST.DATA_AUG             = False
+__C.TEST.DECTECTED_IMAGE_PATH = "./data/detection/"
+__C.TEST.SCORE_THRESHOLD      = 0.3
+__C.TEST.IOU_THRESHOLD        = 0.45
+
+