Einführung

――Ich werde Python nach langer Zeit berühren. Ich bin jetzt süchtig danach, daher möchte ich nur den Inhalt und die Ausführungsergebnisse veröffentlichen und im Laufe der Zeit aktualisieren.

Schließlich zuvor habe ich versucht, das SSD-Modell durch Kopieren und Einfügen zu verschieben, aber ich möchte in der Lage sein, Dinge in mir selbst zu machen. .. ――Dieses Mal wird das VGG16-Modell im Deep-Learning-Modell angewendet, aber es gibt nicht viele, die sorgfältig erklärt werden, was mit TensorFlow implementiert wurde, und das Konzept dieses VGG16-Modells ist auch im SSD-Modell enthalten. Da es enthalten ist, habe ich es als Sprungbrett versucht.
Anfangs wurde es mit TF-Slim implementiert, aber beim Erstellen des Modells ist ein Fehler aufgetreten, sodass es redundant ist Ich habe versucht, es so zu implementieren, wie es ist.

Annahme

In diesem Bereich werden Lerndaten und Lernprogramm verwendet.

Implementierung

Referenz

http://tensorflow.classcat.com/2016/10/18/tensorflow-vgg-model/

Programm

`network.py`


#!/usr/local/bin/python
# -*- coding: utf-8 -*-

import numpy as np
import tensorflow as tf

def vgg16(image, keep_prob):

    def weight_variable(shape):
        initial = tf.truncated_normal(shape, stddev=0.1)
        return tf.Variable(initial)

    def bias_variable(shape):
        initial = tf.constant(0.1, shape=shape)
        return tf.Variable(initial)

    def conv2d(conv, weight):
        return tf.nn.conv2d(conv, weight, strides=[1, 1, 1, 1], padding='SAME')

    def max_pool_2x2(conv):
        return tf.nn.max_pool(conv, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

    with tf.name_scope('conv1_1') as scope:
        weight = weight_variable([3, 3, 3, 64])
        bias = bias_variable([64])
        conv = conv2d(image, weight)
        out = tf.nn.bias_add(conv, bias)
        conv1_1 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv1_2') as scope:
        weight = weight_variable([3, 3, 64, 64])
        bias = bias_variable([64])
        conv = conv2d(conv1_1, weight)
        out = tf.nn.bias_add(conv, bias)
        conv1_2 = tf.nn.relu(out, name=scope)

    with tf.name_scope('pool1') as scope:
        pool1 = max_pool_2x2(conv1_2)

    with tf.name_scope('conv2_1') as scope:
        weight = weight_variable([3, 3, 64, 128])
        bias = bias_variable([128])
        conv = conv2d(pool1, weight)
        out = tf.nn.bias_add(conv, bias)
        conv2_1 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv2_2') as scope:
        weight = weight_variable([3, 3, 128, 128])
        bias = bias_variable([128])
        conv = conv2d(conv2_1, weight)
        out = tf.nn.bias_add(conv, bias)
        conv2_2 = tf.nn.relu(out, name=scope)

    with tf.name_scope('pool2') as scope:
        pool2 = max_pool_2x2(conv2_2)

    with tf.name_scope('conv3_1') as scope:
        weight = weight_variable([3, 3, 128, 256])
        bias = bias_variable([256])
        conv = conv2d(pool2, weight)
        out = tf.nn.bias_add(conv, bias)
        conv3_1 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv3_2') as scope:
        weight = weight_variable([3, 3, 256, 256])
        bias = bias_variable([256])
        conv = conv2d(conv3_1, weight)
        out = tf.nn.bias_add(conv, bias)
        conv3_2 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv3_3') as scope:
        weight = weight_variable([3, 3, 256, 256])
        bias = bias_variable([256])
        conv = conv2d(conv3_2, weight)
        out = tf.nn.bias_add(conv, bias)
        conv3_3 = tf.nn.relu(out, name=scope)

    with tf.name_scope('pool3') as scope:
        pool3 = max_pool_2x2(conv3_3)

    with tf.name_scope('conv4_1') as scope:
        weight = weight_variable([3, 3, 256, 512])
        bias = bias_variable([512])
        conv = conv2d(pool3, weight)
        out = tf.nn.bias_add(conv, bias)
        conv4_1 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv4_2') as scope:
        weight = weight_variable([3, 3, 512, 512])
        bias = bias_variable([512])
        conv = conv2d(conv4_1, weight)
        out = tf.nn.bias_add(conv, bias)
        conv4_2 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv4_3') as scope:
        weight = weight_variable([3, 3, 512, 512])
        bias = bias_variable([512])
        conv = conv2d(conv4_2, weight)
        out = tf.nn.bias_add(conv, bias)
        conv4_3 = tf.nn.relu(out, name=scope)

    with tf.name_scope('pool4') as scope:
        pool4 = max_pool_2x2(conv4_3)

    with tf.name_scope('conv5_1') as scope:
        weight = weight_variable([3, 3, 512, 512])
        bias = bias_variable([512])
        conv = conv2d(pool4, weight)
        out = tf.nn.bias_add(conv, bias)
        conv5_1 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv5_2') as scope:
        weight = weight_variable([3, 3, 512, 512])
        bias = bias_variable([512])
        conv = conv2d(conv5_1, weight)
        out = tf.nn.bias_add(conv, bias)
        conv5_2 = tf.nn.relu(out, name=scope)

    with tf.name_scope('conv5_3') as scope:
        weight = weight_variable([3, 3, 512, 512])
        bias = bias_variable([512])
        conv = conv2d(conv5_2, weight)
        out = tf.nn.bias_add(conv, bias)
        conv5_3 = tf.nn.relu(out, name=scope)

    with tf.name_scope('pool5') as scope:
        pool5 = max_pool_2x2(conv5_3)

    with tf.name_scope('fc6') as scope:
        shape = int(np.prod(pool5.get_shape()[1:]))
        weight = weight_variable([shape, 4096])
        bias = bias_variable([4096])
        pool5_flat = tf.reshape(pool5, [-1, shape])
        fc6 = tf.nn.relu(tf.nn.bias_add(tf.matmul(pool5_flat, weight), bias))
        # fc6_drop = tf.nn.dropout(fc6, keep_prob)

    with tf.name_scope('fc7') as scope:
        weight = weight_variable([4096, 4096])
        bias = bias_variable([4096])
        fc7 = tf.nn.relu(tf.nn.bias_add(tf.matmul(fc6, weight), bias))
        # fc7_drop = tf.nn.dropout(fc7, keep_prob)

    with tf.name_scope('fc8') as scope:
        weight = weight_variable([4096, 3])
        bias = bias_variable([3])
        fc8 = tf.nn.bias_add(tf.matmul(fc7, weight), bias)

    with tf.name_scope('softmax') as scope:
        probs = tf.nn.softmax(fc8)

    return probs

Ausführungsergebnis

Lernen geht überhaupt nicht weiter!

2017-08-01 17:39:33.518478: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 17:39:33.518513: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 17:39:33.518523: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 17:39:33.518532: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
step 0, training accuracy 0.588235
step 1, training accuracy 0.588235
step 2, training accuracy 0.588235
step 3, training accuracy 0.588235
step 4, training accuracy 0.588235
step 5, training accuracy 0.588235
step 6, training accuracy 0.588235
step 7, training accuracy 0.588235

Visualisierung

Als Komposition scheint es richtig zu sein, aber ...

FireShot Capture 041 - TensorBoard - http___localhost_6006_#graphs.jpg

Was ich versucht habe

Die Bildgröße des VGG-Modells beträgt standardmäßig 224 x 224, was mindestens 48 x 48 zu sein scheint, daher habe ich sie auf 48 oder 224 eingestellt. → Keine Änderung.

――Ich habe versucht, die Anzahl der Schichten zu reduzieren. → Keine Änderung.

――Ich habe die Trainingsdaten geändert. → Keine Änderung.

――Die Notation bleibt gleich, und ich habe sie in die normale CNN-Schicht geändert. → Das Lernen wurde normal durchgeführt.

(ﾟ д ﾟ)

[PYTHON] Ich habe ein VGG16-Modell mit TensorFlow gemacht (unterwegs)