花种类预测

1. 数据集及模型下载

1.1 数据集

CSDN下载：

unzip flower_photos.zip

官网下载：

curl http://download.tensorflow.org/example_images/flower_photos.tgz

tar xzf flower_photos.tgz

解压之后包含 5 个子文件夹，每个子文件夹的名称为一种花的名称，平均每一种花有 734 张图片，每张图片都是 RGB 色彩模式，大小不同。

flower_photos/

daisy/

dandelion/

roses/

sunflowers/

tulips/

1.2 Inception-v3模型下载

wget https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip

unzip inception_dec_2015.zip

解压后有两个文件，将要使用的是 .pb 文件：

2. 目录结构

将数据集及模型文件下载好之后，分别放在 data/ 和 model/ 文件夹下，然后新建一个 train.py 文件用于实现迁移学习。

还需要新建一个 tmp/bottleneck/ 文件夹用于存放每张图片通过 Inception-v3 模型计算得到的特征向量。该文件夹的结构与 flower_photos 文件夹类似，可以在代码中生成各子文件夹，或者手动创建。

transfer-learning/

data/

flower_photos/

......

tmp/

bottleneck/

......

model/

imagenet_comp_graph_label_strings.txt

tensorflow_inception_graph.pb

train.py

3. 迁移学习训练代码

该代码实现自《TensorFlow：实战Google深度学习框架》 P161页

该迁移学习方法的实现是，替换掉了 Inception-v3 模型的最后一层全连接层。用瓶颈层的输出来训练一个新的全连接层处理花的分类问题。

由于训练数据、验证数据和测试数据都是训练的时候随机分配的，所以训练正确率是不可再现的，并且差距较大，甚至能达到 10% 左右的差距。不过能用这么少的数据集达到 90% 以上的正确率也是很不错了。

import glob

import os.path

import random

import numpy as np

import tensorflow as tf

from tensorflow.python.platform import gfile

# 数据参数

MODEL_DIR = 'model/' # inception-v3模型的文件夹

MODEL_FILE = 'tensorflow_inception_graph.pb' # inception-v3模型文件名

CACHE_DIR = 'data/tmp/bottleneck' # 图像的特征向量保存地址

INPUT_DATA = 'data/flower_photos' # 图片数据文件夹

VALIDATION_PERCENTAGE = 10 # 验证数据的百分比

TEST_PERCENTAGE = 10 # 测试数据的百分比

# inception-v3模型参数

BOTTLENECK_TENSOR_SIZE = 2048 # inception-v3模型瓶颈层的节点个数

BOTTLENECK_TENSOR_NAME = 'pool_3/_reshape:0' # inception-v3模型中代表瓶颈层结果的张量名称

JPEG_DATA_TENSOR_NAME = 'DecodeJpeg/contents:0' # 图像输入张量对应的名称

# 神经网络的训练参数

LEARNING_RATE = 0.01

STEPS = 4000

BATCH = 100

CHECKPOINT_EVERY = 100

NUM_CHECKPOINTS = 5

# 从数据文件夹中读取所有的图片列表并按训练、验证、测试分开

def create_image_lists(validation_percentage, test_percentage):

result = {} # 保存所有图像。key为类别名称。value也是字典，存储了所有的图片名称

sub_dirs = [x[0] for x in os.walk(INPUT_DATA)] # 获取所有子目录

is_root_dir = True # 第一个目录为当前目录，需要忽略

# 分别对每个子目录进行操作

for sub_dir in sub_dirs:

if is_root_dir:

is_root_dir = False

continue

# 获取当前目录下的所有有效图片

extensions = {'jpg', 'jpeg', 'JPG', 'JPEG'}

file_list = [] # 存储所有图像

dir_name = os.path.basename(sub_dir) # 获取路径的最后一个目录名字

for extension in extensions:

file_glob = os.path.join(INPUT_DATA, dir_name, '*.' + extension)

file_list.extend(glob.glob(file_glob))

if not file_list:

continue

# 将当前类别的图片随机分为训练数据集、测试数据集、验证数据集

label_name = dir_name.lower() # 通过目录名获取类别的名称

training_images = []

testing_images = []

validation_images = []

for file_name in file_list:

base_name = os.path.basename(file_name) # 获取该图片的名称

chance = np.random.randint(100) # 随机产生100个数代表百分比

if chance < validation_percentage:

validation_images.append(base_name)

elif chance < (validation_percentage + test_percentage):

testing_images.append(base_name)

else:

training_images.append(base_name)

# 将当前类别的数据集放入结果字典

result[label_name] = {

'dir': dir_name,

'training': training_images,

'testing': testing_images,

'validation': validation_images

}

# 返回整理好的所有数据

return result

# 通过类别名称、所属数据集、图片编号获取一张图片的地址

def get_image_path(image_lists, image_dir, label_name, index, category):

label_lists = image_lists[label_name] # 获取给定类别中的所有图片

category_list = label_lists[category] # 根据所属数据集的名称获取该集合中的全部图片

mod_index = index % len(category_list) # 规范图片的索引

base_name = category_list[mod_index] # 获取图片的文件名

sub_dir = label_lists['dir'] # 获取当前类别的目录名

full_path = os.path.join(image_dir, sub_dir, base_name) # 图片的绝对路径

return full_path

# 通过类别名称、所属数据集、图片编号获取特征向量值的地址

def get_bottleneck_path(image_lists, label_name, index, category):

return get_image_path(image_lists, CACHE_DIR, label_name, index,

category) + '.txt'

# 使用inception-v3处理图片获取特征向量

def run_bottleneck_on_image(sess, image_data, image_data_tensor,

bottleneck_tensor):

bottleneck_values = sess.run(bottleneck_tensor,

{image_data_tensor: image_data})

bottleneck_values = np.squeeze(bottleneck_values) # 将四维数组压缩成一维数组

return bottleneck_values

# 获取一张图片经过inception-v3模型处理后的特征向量

def get_or_create_bottleneck(sess, image_lists, label_name, index, category,

jpeg_data_tensor, bottleneck_tensor):

# 获取一张图片对应的特征向量文件的路径

label_lists = image_lists[label_name]

sub_dir = label_lists['dir']

sub_dir_path = os.path.join(CACHE_DIR, sub_dir)

if not os.path.exists(sub_dir_path):

os.makedirs(sub_dir_path)

bottleneck_path = get_bottleneck_path(image_lists, label_name, index,

category)

# 如果该特征向量文件不存在，则通过inception-v3模型计算并保存

if not os.path.exists(bottleneck_path):

image_path = get_image_path(image_lists, INPUT_DATA, label_name, index,

category) # 获取图片原始路径

image_data = gfile.FastGFile(image_path, 'rb').read() # 获取图片内容

bottleneck_values = run_bottleneck_on_image(

sess, image_data, jpeg_data_tensor,

bottleneck_tensor) # 通过inception-v3计算特征向量

# 将特征向量存入文件

bottleneck_string = ','.join(str(x) for x in bottleneck_values)

with open(bottleneck_path, 'w') as bottleneck_file:

bottleneck_file.write(bottleneck_string)

else:

# 否则直接从文件中获取图片的特征向量

with open(bottleneck_path, 'r') as bottleneck_file:

bottleneck_string = bottleneck_file.read()

bottleneck_values = [float(x) for x in bottleneck_string.split(',')]

# 返回得到的特征向量

return bottleneck_values

# 随机获取一个batch图片作为训练数据

def get_random_cached_bottlenecks(sess, n_classes, image_lists, how_many,

category, jpeg_data_tensor,

bottleneck_tensor):

bottlenecks = []

ground_truths = []

for _ in range(how_many):

# 随机一个类别和图片编号加入当前的训练数据

label_index = random.randrange(n_classes)

label_name = list(image_lists.keys())[label_index]

image_index = random.randrange(65535)

bottleneck = get_or_create_bottleneck(

sess, image_lists, label_name, image_index, category,

jpeg_data_tensor, bottleneck_tensor)

ground_truth = np.zeros(n_classes, dtype=np.float32)

ground_truth[label_index] = 1.0

bottlenecks.append(bottleneck)

ground_truths.append(ground_truth)

return bottlenecks, ground_truths

# 获取全部的测试数据

def get_test_bottlenecks(sess, image_lists, n_classes, jpeg_data_tensor,

bottleneck_tensor):

bottlenecks = []

ground_truths = []

label_name_list = list(image_lists.keys())

# 枚举所有的类别和每个类别中的测试图片

for label_index, label_name in enumerate(label_name_list):

category = 'testing'

for index, unused_base_name in enumerate(

image_lists[label_name][category]):

bottleneck = get_or_create_bottleneck(

sess, image_lists, label_name, index, category,

jpeg_data_tensor, bottleneck_tensor)

ground_truth = np.zeros(n_classes, dtype=np.float32)

ground_truth[label_index] = 1.0

bottlenecks.append(bottleneck)

ground_truths.append(ground_truth)

return bottlenecks, ground_truths

def main(_):

# 读取所有的图片

image_lists = create_image_lists(VALIDATION_PERCENTAGE, TEST_PERCENTAGE)

n_classes = len(image_lists.keys())

with tf.Graph().as_default() as graph:

# 读取训练好的inception-v3模型

with gfile.FastGFile(os.path.join(MODEL_DIR, MODEL_FILE), 'rb') as f:

graph_def = tf.GraphDef()

graph_def.ParseFromString(f.read())

# 加载inception-v3模型，并返回数据输入张量和瓶颈层输出张量

bottleneck_tensor, jpeg_data_tensor = tf.import_graph_def(

graph_def,

return_elements=[

BOTTLENECK_TENSOR_NAME, JPEG_DATA_TENSOR_NAME

])

# 定义新的神经网络输入

bottleneck_input = tf.placeholder(

tf.float32, [None, BOTTLENECK_TENSOR_SIZE],

name='BottleneckInputPlaceholder')

# 定义新的标准答案输入

ground_truth_input = tf.placeholder(

tf.float32, [None, n_classes], name='GroundTruthInput')

# 定义一层全连接层解决新的图片分类问题

with tf.name_scope('final_training_ops'):

weights = tf.Variable(

tf.truncated_normal(

[BOTTLENECK_TENSOR_SIZE, n_classes], stddev=0.1))

biases = tf.Variable(tf.zeros([n_classes]))

logits = tf.matmul(bottleneck_input, weights) + biases

final_tensor = tf.nn.softmax(logits)

# 定义交叉熵损失函数

cross_entropy = tf.nn.softmax_cross_entropy_with_logits(

logits=logits, labels=ground_truth_input)

cross_entropy_mean = tf.reduce_mean(cross_entropy)

train_step = tf.train.GradientDescentOptimizer(LEARNING_RATE).minimize(

cross_entropy_mean)

# 计算正确率

with tf.name_scope('evaluation'):

correct_prediction = tf.equal(

tf.argmax(final_tensor, 1), tf.argmax(ground_truth_input, 1))

evaluation_step = tf.reduce_mean(

tf.cast(correct_prediction, tf.float32))

# 训练过程

with tf.Session(graph=graph) as sess:

init = tf.global_variables_initializer().run()

# 模型和摘要的保存目录

import time

timestamp = str(int(time.time()))

out_dir = os.path.abspath(

os.path.join(os.path.curdir, 'runs', timestamp))

print('nWriting to {}n'.format(out_dir))

# 损失值和正确率的摘要

loss_summary = tf.summary.scalar('loss', cross_entropy_mean)

acc_summary = tf.summary.scalar('accuracy', evaluation_step)

# 训练摘要

train_summary_op = tf.summary.merge([loss_summary, acc_summary])

train_summary_dir = os.path.join(out_dir, 'summaries', 'train')

train_summary_writer = tf.summary.FileWriter(train_summary_dir,

sess.graph)

# 开发摘要

dev_summary_op = tf.summary.merge([loss_summary, acc_summary])

dev_summary_dir = os.path.join(out_dir, 'summaries', 'dev')

dev_summary_writer = tf.summary.FileWriter(dev_summary_dir, sess.graph)

# 保存检查点

checkpoint_dir = os.path.abspath(os.path.join(out_dir, 'checkpoints'))

checkpoint_prefix = os.path.join(checkpoint_dir, 'model')

if not os.path.exists(checkpoint_dir):

os.makedirs(checkpoint_dir)

saver = tf.train.Saver(

tf.global_variables(), max_to_keep=NUM_CHECKPOINTS)

for i in range(STEPS):

# 每次获取一个batch的训练数据

train_bottlenecks, train_ground_truth = get_random_cached_bottlenecks(

sess, n_classes, image_lists, BATCH, 'training',

jpeg_data_tensor, bottleneck_tensor)

_, train_summaries = sess.run(

[train_step, train_summary_op],

feed_dict={

bottleneck_input: train_bottlenecks,

ground_truth_input: train_ground_truth

})

# 保存每步的摘要

train_summary_writer.add_summary(train_summaries, i)

# 在验证集上测试正确率

if i % 100 == 0 or i + 1 == STEPS:

validation_bottlenecks, validation_ground_truth = get_random_cached_bottlenecks(

sess, n_classes, image_lists, BATCH, 'validation',

jpeg_data_tensor, bottleneck_tensor)

validation_accuracy, dev_summaries = sess.run(

[evaluation_step, dev_summary_op],

feed_dict={

bottleneck_input: validation_bottlenecks,

ground_truth_input: validation_ground_truth

})

print(

'Step %d : Validation accuracy on random sampled %d examples = %.1f%%'

% (i, BATCH, validation_accuracy * 100))

# 每隔checkpoint_every保存一次模型和测试摘要

if i % CHECKPOINT_EVERY == 0:

dev_summary_writer.add_summary(dev_summaries, i)

path = saver.save(sess, checkpoint_prefix, global_step=i)

print('Saved model checkpoint to {}n'.format(path))

# 最后在测试集上测试正确率

test_bottlenecks, test_ground_truth = get_test_bottlenecks(

sess, image_lists, n_classes, jpeg_data_tensor, bottleneck_tensor)

test_accuracy = sess.run(

evaluation_step,

feed_dict={

bottleneck_input: test_bottlenecks,

ground_truth_input: test_ground_truth

})

print('Final test accuracy = %.1f%%' % (test_accuracy * 100))

# 保存标签

output_labels = os.path.join(out_dir, 'labels.txt')

with tf.gfile.FastGFile(output_labels, 'w') as f:

keys = list(image_lists.keys())

for i in range(len(keys)):

keys[i] = '%2d -> %s' % (i, keys[i])

f.write('n'.join(keys) + 'n')

if __name__ == '__main__':

tf.app.run()

4. 运行

运行 train.py ，迭代4000次的结果如下：

Step 0 : Validation accuracy on random sampled 100 examples = 15.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-0

Step 100 : Validation accuracy on random sampled 100 examples = 67.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-100

Step 200 : Validation accuracy on random sampled 100 examples = 82.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-200

Step 300 : Validation accuracy on random sampled 100 examples = 83.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-300

Step 400 : Validation accuracy on random sampled 100 examples = 91.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-400

Step 500 : Validation accuracy on random sampled 100 examples = 89.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-500

Step 600 : Validation accuracy on random sampled 100 examples = 85.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-600

Step 700 : Validation accuracy on random sampled 100 examples = 91.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-700

Step 800 : Validation accuracy on random sampled 100 examples = 86.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-800

Step 900 : Validation accuracy on random sampled 100 examples = 92.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-900

Step 1000 : Validation accuracy on random sampled 100 examples = 89.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1000

Step 1100 : Validation accuracy on random sampled 100 examples = 88.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1100

Step 1200 : Validation accuracy on random sampled 100 examples = 93.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1200

Step 1300 : Validation accuracy on random sampled 100 examples = 94.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1300

Step 1400 : Validation accuracy on random sampled 100 examples = 92.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1400

Step 1500 : Validation accuracy on random sampled 100 examples = 95.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1500

Step 1600 : Validation accuracy on random sampled 100 examples = 98.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1600

Step 1700 : Validation accuracy on random sampled 100 examples = 95.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1700

Step 1800 : Validation accuracy on random sampled 100 examples = 96.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1800

Step 1900 : Validation accuracy on random sampled 100 examples = 88.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-1900

Step 2000 : Validation accuracy on random sampled 100 examples = 97.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2000

Step 2100 : Validation accuracy on random sampled 100 examples = 92.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2100

Step 2200 : Validation accuracy on random sampled 100 examples = 93.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2200

Step 2300 : Validation accuracy on random sampled 100 examples = 92.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2300

Step 2400 : Validation accuracy on random sampled 100 examples = 95.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2400

Step 2500 : Validation accuracy on random sampled 100 examples = 91.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2500

Step 2600 : Validation accuracy on random sampled 100 examples = 93.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2600

Step 2700 : Validation accuracy on random sampled 100 examples = 93.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2700

Step 2800 : Validation accuracy on random sampled 100 examples = 94.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2800

Step 2900 : Validation accuracy on random sampled 100 examples = 93.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-2900

Step 3000 : Validation accuracy on random sampled 100 examples = 91.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3000

Step 3100 : Validation accuracy on random sampled 100 examples = 96.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3100

Step 3200 : Validation accuracy on random sampled 100 examples = 94.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3200

Step 3300 : Validation accuracy on random sampled 100 examples = 94.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3300

Step 3400 : Validation accuracy on random sampled 100 examples = 94.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3400

Step 3500 : Validation accuracy on random sampled 100 examples = 93.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3500

Step 3600 : Validation accuracy on random sampled 100 examples = 89.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3600

Step 3700 : Validation accuracy on random sampled 100 examples = 92.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3700

Step 3800 : Validation accuracy on random sampled 100 examples = 89.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3800

Step 3900 : Validation accuracy on random sampled 100 examples = 92.0%

Saved model checkpoint to D:MyCodeuntitledflowerruns1541938070checkpointsmodel-3900

Step 3999 : Validation accuracy on random sampled 100 examples = 96.0%

Final test accuracy = 92.3%

然后打开 TensorBoard：

tensorboard --logdir=./runs/1521208186(这里换成你自己的)/summaries/train

保存的模型和摘要如图所示：

测试集的准确率和loss：

运行：

tensorboard --logdir=./runs/1521208186(这里换成你自己的)/summaries/dev

验证集的准确率和loss：

5. 测试

由于迁移训练时使用的是 inception-v3 模型的特征向量作为新的全连接层的输入，所以测试的步骤与常规的不太一样：

测试时需要先加载 inception-v3 模型，从而获取图像的特征向量

然后再加载迁移训练的模型，将特征向量作为输入，得到预测值

代码如下：

import tensorflow as tf

import numpy as np

# 模型目录

CHECKPOINT_DIR = './runs/1541938070/checkpoints'#这里需要自己修改一下INCEPTION_MODEL_FILE = 'model/tensorflow_inception_graph.pb'

# inception-v3模型参数

BOTTLENECK_TENSOR_NAME = 'pool_3/_reshape:0' # inception-v3模型中代表瓶颈层结果的张量名称

JPEG_DATA_TENSOR_NAME = 'DecodeJpeg/contents:0' # 图像输入张量对应的名称

# 测试数据

file_path = './data/flower_photos/tulips/11746080_963537acdc.jpg'

y_test = [4]

# 读取数据

image_data = tf.gfile.FastGFile(file_path, 'rb').read()

# 评估

checkpoint_file = tf.train.latest_checkpoint(CHECKPOINT_DIR)

with tf.Graph().as_default() as graph:

with tf.Session().as_default() as sess:

# 读取训练好的inception-v3模型

with tf.gfile.FastGFile(INCEPTION_MODEL_FILE, 'rb') as f:

graph_def = tf.GraphDef()

graph_def.ParseFromString(f.read())

# 加载inception-v3模型，并返回数据输入张量和瓶颈层输出张量

bottleneck_tensor, jpeg_data_tensor = tf.import_graph_def(

graph_def,

return_elements=[BOTTLENECK_TENSOR_NAME, JPEG_DATA_TENSOR_NAME])

# 使用inception-v3处理图片获取特征向量

bottleneck_values = sess.run(bottleneck_tensor,

{jpeg_data_tensor: image_data})

# 将四维数组压缩成一维数组，由于全连接层输入时有batch的维度，所以用列表作为输入

bottleneck_values = [np.squeeze(bottleneck_values)]

# 加载元图和变量

saver = tf.train.import_meta_graph('{}.meta'.format(checkpoint_file))

saver.restore(sess, checkpoint_file)

# 通过名字从图中获取输入占位符

input_x = graph.get_operation_by_name(

'BottleneckInputPlaceholder').outputs[0]

# 我们想要评估的tensors

predictions = graph.get_operation_by_name('evaluation/ArgMax').outputs[

0]

# 收集预测值

all_predictions = []

all_predictions = sess.run(predictions, {input_x: bottleneck_values})

# 如果提供了标签则打印正确率

if y_test is not None:

correct_predictions = float(sum(all_predictions == y_test))

print('nTotal number of test examples: {}'.format(len(y_test)))

print('Accuracy: {:g}'.format(correct_predictions / float(len(y_test))))

样例测试结果如下：

$ python eval.py

Total number of test examples: 1

Accuracy: 1

相关知识

【机器学习】应用KNN实现鸢尾花种类预测
【机器学习小实验5】基于决策树和随机森林的鸢尾花种类预测
：花芸豆主要病虫害预测预报技术规程
紫薇花病虫害预测预报（8页）
洋甘菊花蜡市场规模预测
植物病害预测
病虫害预测
植物病虫害预测预报最新
病虫害预测预警系统
病害调查与预测ppt课件

网址: 花种类预测 https://www.huajiangbk.com/newsview1057228.html