CV之CNN：基于tensorflow框架采用CNN(改進的AlexNet,訓練/評估/推理)卷積神經網絡算法實現貓狗圖像分類識別

目錄

基于tensorflow框架采用CNN(改進的AlexNet,訓練/評估/推理)卷積神經網絡算法實現貓狗圖像分類識別

數據集介紹

輸出結果

使用model.ckpt-6000模型預測

?預測錯誤的只有一個案例，如下所示

訓練結果

核心代碼

---

基于tensorflow框架采用CNN(改進的AlexNet,訓練/評估/推理)卷積神經網絡算法實現貓狗圖像分類識別

數據集介紹

數據下載：Dogs vs. Cats Redux: Kernels Edition | Kaggle

? ? ?train文件夾里有25000張狗和貓的圖片。這個文件夾中的每個圖像都有標簽作為文件名的一部分。測試文件夾包含12500張圖片，根據數字id命名。對于測試集中的每個圖像，您應該預測圖像是一只狗的概率(1 =狗，0 =貓)。

輸出結果

使用model.ckpt-6000模型預測

?預測錯誤的只有一個案例，如下所示

序號		使用model.ckpt-4000模型預測	使用model.ckpt-6000模型預測	使用model.ckpt-8000模型預測	使用model.ckpt-10000模型預測	使用model.ckpt-12000模型預測
1	cat	cat (1).jpg 貓的概率 0.631	cat (1).jpg 狗的概率 0.740	cat (1).jpg 狗的概率 0.781	cat (1).jpg 狗的概率 0.976	cat (1).jpg 狗的概率 0.991
2		cat (10).jpg 狗的概率 0.697	cat (10).jpg 貓的概率 0.566	cat (10).jpg 貓的概率 0.925	cat (10).jpg 貓的概率 0.925	cat (10).jpg 貓的概率 0.816
3		cat (11).jpg 貓的概率 0.927	cat (11).jpg 貓的概率 0.988	cat (11).jpg 貓的概率 1.000	cat (11).jpg 貓的概率 1.000	cat (11).jpg 貓的概率 1.000
4		cat (12).jpg 狗的概率 0.746	cat (12).jpg 狗的概率 0.723	cat (12).jpg 狗的概率 0.822	cat (12).jpg 狗的概率 0.998	cat (12).jpg 狗的概率 1.000
5		cat (13).jpg 貓的概率 0.933	cat (13).jpg 貓的概率 0.983	cat (13).jpg 貓的概率 0.997	cat (13).jpg 貓的概率 1.000	cat (13).jpg 貓的概率 1.000
6		cat (14).jpg 狗的概率 0.657	cat (14).jpg 貓的概率 0.597	cat (14).jpg 狗的概率 0.758	cat (14).jpg 狗的概率 0.695	cat (14).jpg 貓的概率 0.544
7		cat (15).jpg 狗的概率 0.578	cat (15).jpg 狗的概率 0.535	cat (15).jpg 狗的概率 0.526	cat (15).jpg 狗的概率 0.750	cat (15).jpg 狗的概率 0.569
8		cat (2).jpg 貓的概率 0.649	cat (2).jpg 貓的概率 0.637	cat (2).jpg 貓的概率 0.844	cat (2).jpg 貓的概率 0.996	cat (2).jpg 貓的概率 0.998
9		cat (3).jpg 狗的概率 0.668	cat (3).jpg 貓的概率 0.538	cat (3).jpg 貓的概率 0.710	cat (3).jpg 貓的概率 0.968	cat (3).jpg 貓的概率 0.995
10		cat (4).jpg 狗的概率 0.856	cat (4).jpg 狗的概率 0.780	cat (4).jpg 狗的概率 0.831	cat (4).jpg 狗的概率 0.974	cat (4).jpg 狗的概率 0.976
11		cat (5).jpg 貓的概率 0.812	cat (5).jpg 貓的概率 0.776	cat (5).jpg 貓的概率 0.505	cat (5).jpg 貓的概率 0.732	cat (5).jpg 狗的概率 0.608
12		cat (6).jpg 貓的概率 0.524	cat (6).jpg 狗的概率 0.661	cat (6).jpg 狗的概率 0.748	cat (6).jpg 狗的概率 0.970	cat (6).jpg 狗的概率 0.987
13		cat (7).jpg 狗的概率 0.612	cat (7).jpg 貓的概率 0.845	cat (7).jpg 貓的概率 0.894	cat (7).jpg 貓的概率 0.987	cat (7).jpg 貓的概率 0.728
14		cat (8).jpg 狗的概率 0.823	cat (8).jpg 狗的概率 0.948	cat (8).jpg 狗的概率 0.920	cat (8).jpg 狗的概率 0.982	cat (8).jpg 狗的概率 0.999
15		cat (9).jpg 貓的概率 0.697	cat (9).jpg 貓的概率 0.704	cat (9).jpg 狗的概率 0.819	cat (9).jpg 貓的概率 0.930	cat (9).jpg 狗的概率 0.718
16	dog	dog (1).jpg 狗的概率 0.987	dog (1).jpg 狗的概率 0.995	dog (1).jpg 狗的概率 0.999	dog (1).jpg 狗的概率 1.000	dog (1).jpg 狗的概率 1.000
17		dog (10).jpg 狗的概率 0.628	dog (10).jpg 貓的概率 0.629	dog (10).jpg 貓的概率 0.994	dog (10).jpg 貓的概率 1.000	dog (10).jpg 貓的概率 1.000
18		dog (11).jpg 狗的概率 0.804	dog (11).jpg 狗的概率 0.879	dog (11).jpg 狗的概率 0.993	dog (11).jpg 狗的概率 1.000	dog (11).jpg 狗的概率 1.000
19		dog (12).jpg 貓的概率 0.704	dog (12).jpg 貓的概率 0.758	dog (12).jpg 狗的概率 0.503	dog (12).jpg 狗的概率 0.653	dog (12).jpg 貓的概率 0.985
20		dog (13).jpg 狗的概率 0.987	dog (13).jpg 狗的概率 0.997	dog (13).jpg 狗的概率 1.000	dog (13).jpg 狗的概率 1.000	dog (13).jpg 狗的概率 1.000
21		dog (14).jpg 狗的概率 0.815	dog (14).jpg 狗的概率 0.844	dog (14).jpg 狗的概率 0.904	dog (14).jpg 狗的概率 0.996	dog (14).jpg 狗的概率 0.950
22		dog (15).jpg 狗的概率 0.917	dog (15).jpg 狗的概率 0.984	dog (15).jpg 狗的概率 0.999	dog (15).jpg 狗的概率 1.000	dog (15).jpg 狗的概率 1.000
23		dog (16).jpg 狗的概率 0.883	dog (16).jpg 狗的概率 0.931	dog (16).jpg 狗的概率 0.830	dog (16).jpg 狗的概率 0.975	dog (16).jpg 狗的概率 0.983
24		dog (2).jpg 狗的概率 0.934	dog (2).jpg 狗的概率 0.982	dog (2).jpg 狗的概率 0.998	dog (2).jpg 狗的概率 1.000	dog (2).jpg 狗的概率 1.000
25		dog (3).jpg 狗的概率 0.993	dog (3).jpg 狗的概率 1.000	dog (3).jpg 狗的概率 1.000	dog (3).jpg 狗的概率 1.000	dog (3).jpg 狗的概率 1.000
26		dog (4).jpg 狗的概率 0.693	dog (4).jpg 狗的概率 0.754	dog (4).jpg 狗的概率 0.976	dog (4).jpg 狗的概率 0.515	dog (4).jpg 狗的概率 0.995
27		dog (5).jpg 狗的概率 0.916	dog (5).jpg 狗的概率 0.976	dog (5).jpg 狗的概率 0.993	dog (5).jpg 狗的概率 0.998	dog (5).jpg 狗的概率 1.000
28		dog (6).jpg 狗的概率 0.947	dog (6).jpg 狗的概率 0.989	dog (6).jpg 狗的概率 0.999	dog (6).jpg 狗的概率 1.000	dog (6).jpg 狗的概率 1.000
29		dog (7).jpg 貓的概率 0.526	dog (7).jpg 貓的概率 0.685	dog (7).jpg 貓的概率 0.961	dog (7).jpg 貓的概率 1.000	dog (7).jpg 貓的概率 1.000
30		dog (8).jpg 狗的概率 0.981	dog (8).jpg 狗的概率 0.998	dog (8).jpg 狗的概率 1.000	dog (8).jpg 狗的概率 1.000	dog (8).jpg 狗的概率 1.000
31		dog (9).jpg 狗的概率 0.899	dog (9).jpg 狗的概率 0.983	dog (9).jpg 狗的概率 0.999	dog (9).jpg 狗的概率 1.000	dog (9).jpg 狗的概率 1.000

訓練結果

Step 0, train loss = 0.69, train accuracy = 78.12% Step 50, train loss = 0.69, train accuracy = 43.75% Step 100, train loss = 0.70, train accuracy = 46.88% Step 150, train loss = 0.65, train accuracy = 75.00% Step 200, train loss = 0.66, train accuracy = 59.38% Step 250, train loss = 0.66, train accuracy = 62.50% Step 300, train loss = 0.72, train accuracy = 40.62% Step 350, train loss = 0.66, train accuracy = 62.50% Step 400, train loss = 0.58, train accuracy = 68.75% Step 450, train loss = 0.70, train accuracy = 65.62% Step 500, train loss = 0.68, train accuracy = 56.25% Step 550, train loss = 0.51, train accuracy = 81.25% Step 600, train loss = 0.54, train accuracy = 75.00% Step 650, train loss = 0.64, train accuracy = 68.75% Step 700, train loss = 0.69, train accuracy = 53.12% Step 750, train loss = 0.57, train accuracy = 71.88% Step 800, train loss = 0.80, train accuracy = 50.00% Step 850, train loss = 0.62, train accuracy = 59.38% Step 900, train loss = 0.59, train accuracy = 65.62% Step 950, train loss = 0.54, train accuracy = 71.88% Step 1000, train loss = 0.57, train accuracy = 68.75% Step 1050, train loss = 0.56, train accuracy = 78.12% Step 1100, train loss = 0.66, train accuracy = 59.38% Step 1150, train loss = 0.50, train accuracy = 84.38% Step 1200, train loss = 0.46, train accuracy = 81.25% Step 1250, train loss = 0.57, train accuracy = 59.38% Step 1300, train loss = 0.37, train accuracy = 81.25% Step 1350, train loss = 0.64, train accuracy = 62.50% Step 1400, train loss = 0.44, train accuracy = 81.25% Step 1450, train loss = 0.46, train accuracy = 84.38% Step 1500, train loss = 0.50, train accuracy = 71.88% Step 1550, train loss = 0.58, train accuracy = 62.50% Step 1600, train loss = 0.43, train accuracy = 75.00% Step 1650, train loss = 0.55, train accuracy = 71.88% Step 1700, train loss = 0.50, train accuracy = 71.88% Step 1750, train loss = 0.46, train accuracy = 75.00% Step 1800, train loss = 0.81, train accuracy = 53.12% Step 1850, train loss = 0.41, train accuracy = 90.62% Step 1900, train loss = 0.65, train accuracy = 68.75% Step 1950, train loss = 0.37, train accuracy = 84.38% Step 2000, train loss = 0.39, train accuracy = 81.25% Step 2050, train loss = 0.45, train accuracy = 84.38% Step 2100, train loss = 0.44, train accuracy = 78.12% Step 2150, train loss = 0.59, train accuracy = 65.62% Step 2200, train loss = 0.51, train accuracy = 78.12% Step 2250, train loss = 0.42, train accuracy = 81.25% Step 2300, train loss = 0.32, train accuracy = 87.50% Step 2350, train loss = 0.48, train accuracy = 75.00% Step 2400, train loss = 0.54, train accuracy = 71.88% Step 2450, train loss = 0.51, train accuracy = 71.88% Step 2500, train loss = 0.73, train accuracy = 59.38% Step 2550, train loss = 0.52, train accuracy = 78.12% Step 2600, train loss = 0.65, train accuracy = 62.50% Step 2650, train loss = 0.52, train accuracy = 71.88% Step 2700, train loss = 0.48, train accuracy = 71.88% Step 2750, train loss = 0.37, train accuracy = 84.38% Step 2800, train loss = 0.46, train accuracy = 78.12% Step 2850, train loss = 0.40, train accuracy = 84.38% Step 2900, train loss = 0.45, train accuracy = 81.25% Step 2950, train loss = 0.36, train accuracy = 84.38% Step 3000, train loss = 0.46, train accuracy = 75.00% Step 3050, train loss = 0.53, train accuracy = 71.88% Step 3100, train loss = 0.37, train accuracy = 84.38% Step 3150, train loss = 0.53, train accuracy = 75.00% Step 3200, train loss = 0.52, train accuracy = 75.00% Step 3250, train loss = 0.62, train accuracy = 65.62% Step 3300, train loss = 0.58, train accuracy = 71.88% Step 3350, train loss = 0.71, train accuracy = 65.62% Step 3400, train loss = 0.43, train accuracy = 78.12% Step 3450, train loss = 0.46, train accuracy = 78.12% Step 3500, train loss = 0.46, train accuracy = 71.88% Step 3550, train loss = 0.53, train accuracy = 68.75% Step 3600, train loss = 0.44, train accuracy = 75.00% Step 3650, train loss = 0.55, train accuracy = 65.62% Step 3700, train loss = 0.62, train accuracy = 75.00% Step 3750, train loss = 0.48, train accuracy = 75.00% Step 3800, train loss = 0.66, train accuracy = 53.12% Step 3850, train loss = 0.53, train accuracy = 75.00% Step 3900, train loss = 0.36, train accuracy = 81.25% Step 3950, train loss = 0.37, train accuracy = 87.50% Step 4000, train loss = 0.46, train accuracy = 78.12% Step 4050, train loss = 0.36, train accuracy = 84.38% Step 4100, train loss = 0.34, train accuracy = 78.12% Step 4150, train loss = 0.48, train accuracy = 78.12% Step 4200, train loss = 0.43, train accuracy = 87.50% Step 4250, train loss = 0.34, train accuracy = 84.38% Step 4300, train loss = 0.28, train accuracy = 87.50% Step 4350, train loss = 0.19, train accuracy = 96.88% Step 4400, train loss = 0.46, train accuracy = 71.88% Step 4450, train loss = 0.33, train accuracy = 84.38% Step 4500, train loss = 0.55, train accuracy = 75.00% Step 4550, train loss = 0.31, train accuracy = 93.75% Step 4600, train loss = 0.30, train accuracy = 84.38% Step 4650, train loss = 0.38, train accuracy = 84.38% Step 4700, train loss = 0.36, train accuracy = 84.38% Step 4750, train loss = 0.32, train accuracy = 87.50% Step 4800, train loss = 0.36, train accuracy = 81.25% Step 4850, train loss = 0.36, train accuracy = 87.50% Step 4900, train loss = 0.49, train accuracy = 71.88% Step 4950, train loss = 0.51, train accuracy = 68.75% Step 5000, train loss = 0.59, train accuracy = 68.75% Step 5050, train loss = 0.55, train accuracy = 75.00% Step 5100, train loss = 0.71, train accuracy = 68.75% Step 5150, train loss = 0.48, train accuracy = 71.88% Step 5200, train loss = 0.39, train accuracy = 90.62% Step 5250, train loss = 0.49, train accuracy = 81.25% Step 5300, train loss = 0.36, train accuracy = 81.25% Step 5350, train loss = 0.31, train accuracy = 90.62% Step 5400, train loss = 0.39, train accuracy = 87.50% Step 5450, train loss = 0.34, train accuracy = 78.12% Step 5500, train loss = 0.29, train accuracy = 84.38% Step 5550, train loss = 0.21, train accuracy = 93.75% Step 5600, train loss = 0.41, train accuracy = 78.12% Step 5650, train loss = 0.38, train accuracy = 84.38% Step 5700, train loss = 0.27, train accuracy = 87.50% Step 5750, train loss = 0.24, train accuracy = 90.62% Step 5800, train loss = 0.17, train accuracy = 96.88% Step 5850, train loss = 0.23, train accuracy = 93.75% Step 5900, train loss = 0.37, train accuracy = 71.88% Step 5950, train loss = 0.49, train accuracy = 71.88% Step 6000, train loss = 0.43, train accuracy = 81.25% Step 6050, train loss = 0.33, train accuracy = 87.50% Step 6100, train loss = 0.46, train accuracy = 75.00% Step 6150, train loss = 0.61, train accuracy = 81.25% Step 6200, train loss = 0.34, train accuracy = 84.38% Step 6250, train loss = 0.63, train accuracy = 71.88% Step 6300, train loss = 0.21, train accuracy = 90.62% Step 6350, train loss = 0.21, train accuracy = 90.62% Step 6400, train loss = 0.27, train accuracy = 87.50% Step 6450, train loss = 0.17, train accuracy = 87.50% Step 6500, train loss = 0.34, train accuracy = 87.50% Step 6550, train loss = 0.34, train accuracy = 87.50% Step 6600, train loss = 0.32, train accuracy = 84.38% Step 6650, train loss = 0.39, train accuracy = 84.38% Step 6700, train loss = 0.38, train accuracy = 84.38% Step 6750, train loss = 0.41, train accuracy = 84.38% Step 6800, train loss = 0.49, train accuracy = 81.25% Step 6850, train loss = 0.36, train accuracy = 84.38% Step 6900, train loss = 0.20, train accuracy = 93.75% Step 6950, train loss = 0.13, train accuracy = 93.75% Step 7000, train loss = 0.31, train accuracy = 87.50% Step 7050, train loss = 0.18, train accuracy = 93.75% Step 7100, train loss = 0.23, train accuracy = 90.62% Step 7150, train loss = 0.13, train accuracy = 96.88% Step 7200, train loss = 0.14, train accuracy = 96.88% Step 7250, train loss = 0.32, train accuracy = 84.38% Step 7300, train loss = 0.18, train accuracy = 93.75% Step 7350, train loss = 0.14, train accuracy = 100.00% Step 7400, train loss = 0.60, train accuracy = 75.00% Step 7450, train loss = 0.20, train accuracy = 93.75% Step 7500, train loss = 0.13, train accuracy = 93.75% Step 7550, train loss = 0.22, train accuracy = 90.62% Step 7600, train loss = 0.13, train accuracy = 96.88% Step 7650, train loss = 0.20, train accuracy = 93.75% Step 7700, train loss = 0.24, train accuracy = 90.62% Step 7750, train loss = 0.19, train accuracy = 93.75% Step 7800, train loss = 0.16, train accuracy = 93.75% Step 7850, train loss = 0.08, train accuracy = 100.00% Step 7900, train loss = 0.10, train accuracy = 96.88% Step 7950, train loss = 0.13, train accuracy = 93.75% Step 8000, train loss = 0.18, train accuracy = 90.62% Step 8050, train loss = 0.27, train accuracy = 93.75% Step 8100, train loss = 0.04, train accuracy = 100.00% Step 8150, train loss = 0.27, train accuracy = 87.50% Step 8200, train loss = 0.06, train accuracy = 96.88% Step 8250, train loss = 0.12, train accuracy = 100.00% Step 8300, train loss = 0.28, train accuracy = 87.50% Step 8350, train loss = 0.24, train accuracy = 90.62% Step 8400, train loss = 0.16, train accuracy = 93.75% Step 8450, train loss = 0.11, train accuracy = 93.75% Step 8500, train loss = 0.13, train accuracy = 96.88% Step 8550, train loss = 0.05, train accuracy = 100.00% Step 8600, train loss = 0.10, train accuracy = 93.75% Step 8650, train loss = 0.14, train accuracy = 100.00% Step 8700, train loss = 0.21, train accuracy = 90.62% Step 8750, train loss = 0.09, train accuracy = 96.88% Step 8800, train loss = 0.11, train accuracy = 96.88% Step 8850, train loss = 0.10, train accuracy = 96.88% Step 8900, train loss = 0.12, train accuracy = 93.75% Step 8950, train loss = 0.48, train accuracy = 81.25% Step 9000, train loss = 0.07, train accuracy = 100.00% Step 9050, train loss = 0.03, train accuracy = 100.00% Step 9100, train loss = 0.10, train accuracy = 93.75% Step 9150, train loss = 0.05, train accuracy = 96.88% Step 9200, train loss = 0.04, train accuracy = 100.00% Step 9250, train loss = 0.03, train accuracy = 100.00% Step 9300, train loss = 0.04, train accuracy = 96.88% Step 9350, train loss = 0.08, train accuracy = 100.00% Step 9400, train loss = 0.05, train accuracy = 100.00% Step 9450, train loss = 0.15, train accuracy = 90.62% Step 9500, train loss = 0.03, train accuracy = 100.00% Step 9550, train loss = 0.05, train accuracy = 100.00% Step 9600, train loss = 0.15, train accuracy = 96.88% Step 9650, train loss = 0.03, train accuracy = 100.00% Step 9700, train loss = 0.02, train accuracy = 100.00% Step 9750, train loss = 0.08, train accuracy = 96.88% Step 9800, train loss = 0.04, train accuracy = 100.00% Step 9850, train loss = 0.06, train accuracy = 96.88% Step 9900, train loss = 0.03, train accuracy = 100.00% Step 9950, train loss = 0.03, train accuracy = 100.00% Step 10000, train loss = 0.11, train accuracy = 93.75% Step 10050, train loss = 0.02, train accuracy = 100.00% Step 10100, train loss = 0.01, train accuracy = 100.00% Step 10150, train loss = 0.05, train accuracy = 96.88% Step 10200, train loss = 0.07, train accuracy = 96.88% Step 10250, train loss = 0.06, train accuracy = 96.88% Step 10300, train loss = 0.03, train accuracy = 100.00% Step 10350, train loss = 0.08, train accuracy = 96.88% Step 10400, train loss = 0.05, train accuracy = 96.88% Step 10450, train loss = 0.02, train accuracy = 100.00% Step 10500, train loss = 0.22, train accuracy = 93.75% Step 10550, train loss = 0.06, train accuracy = 100.00% Step 10600, train loss = 0.02, train accuracy = 100.00% Step 10650, train loss = 0.02, train accuracy = 100.00% Step 10700, train loss = 0.03, train accuracy = 100.00% Step 10750, train loss = 0.15, train accuracy = 96.88% Step 10800, train loss = 0.05, train accuracy = 100.00% Step 10850, train loss = 0.02, train accuracy = 100.00% Step 10900, train loss = 0.04, train accuracy = 96.88% Step 10950, train loss = 0.05, train accuracy = 96.88% Step 11000, train loss = 0.02, train accuracy = 100.00% Step 11050, train loss = 0.10, train accuracy = 96.88% Step 11100, train loss = 0.08, train accuracy = 96.88% Step 11150, train loss = 0.02, train accuracy = 100.00% Step 11200, train loss = 0.01, train accuracy = 100.00% Step 11250, train loss = 0.06, train accuracy = 96.88% Step 11300, train loss = 0.18, train accuracy = 93.75% Step 11350, train loss = 0.02, train accuracy = 100.00% Step 11400, train loss = 0.04, train accuracy = 100.00% Step 11450, train loss = 0.03, train accuracy = 100.00% Step 11500, train loss = 0.01, train accuracy = 100.00% Step 11550, train loss = 0.02, train accuracy = 100.00%

核心代碼

weights = tf.get_variable('weights', shape=[3, 3, 3, 16], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[16], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) conv = tf.nn.conv2d(images, weights, strides=[1, 1, 1, 1], padding='SAME') pre_activation = tf.nn.bias_add(conv, biases) conv1 = tf.nn.relu(pre_activation, name=scope.name) with tf.variable_scope('pooling1_lrn') as scope: pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name='pooling1') norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm1') with tf.variable_scope('conv2') as scope: weights = tf.get_variable('weights', shape=[3, 3, 16, 16], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[16], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) conv = tf.nn.conv2d(norm1, weights, strides=[1, 1, 1, 1], padding='SAME') pre_activation = tf.nn.bias_add(conv, biases) conv2 = tf.nn.relu(pre_activation, name='conv2') with tf.variable_scope('pooling2_lrn') as scope: norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm2') pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME', name='pooling2') with tf.variable_scope('local3') as scope: reshape = tf.reshape(pool2, shape=[batch_size, -1]) dim = reshape.get_shape()[1].value weights = tf.get_variable('weights', shape=[dim, 128], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[128], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name) # local4 with tf.variable_scope('local4') as scope: weights = tf.get_variable('weights', shape=[128, 128], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[128], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4') with tf.variable_scope('softmax_linear') as scope: weights = tf.get_variable('softmax_linear', shape=[128, n_classes], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32)) biases = tf.get_variable('biases', shape=[n_classes], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear')

總結

以上是生活随笔為你收集整理的CV之CNN：基于tensorflow框架采用CNN(改进的AlexNet,训练/评估/推理)卷积神经网络算法实现猫狗图像分类识别的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。