我正在使用tensorflow 1.10 Python 3.6
我的代码基于TensorFlow提供的预制iris classification model。这意味着，我正在使用Tensorflow DNN预制分类器，具有以下区别：
可以从以下链接下载测试和培训文件： https://www.dropbox.com/sh/nmu8i2i8xe6hvfq/AADQEOIHH8e-kUHQf8zmmDMDa?dl=0
我已经编写了代码将此分类器导出为tflite格式，但是python模型中的准确性高于75％，但是当导出的准确性下降到约45％时，这意味着约有30％的准确性丢失（这是太多了）。 我尝试了使用不同数据集的代码，在所有这些代码中，导出后的准确性降低了很多！ 这使我认为TocoConverter函数出了点问题，或者我可能错误地导出到tflite，缺少参数或类似的东西。
这是我生成模型的方式：
classifier = tf.estimator.DNNClassifier(
feature_columns=my_feature_columns,
hidden_units=[100, 500],
optimizer=tf.train.AdagradOptimizer(learning_rate=0.003),
n_classes=num_labels,
model_dir="myModel")
这是我用来转换为tflite的函数：
converter = tf.contrib.lite.TocoConverter.from_frozen_graph(final_model_path, input_arrays, output_arrays, input_shapes={"dnn/input_from_feature_columns/input_layer/concat": [1, 10]})
tflite_model = converter.convert()
我分享了完整的代码，在其中我还计算了生成的.tflite文件的准确性。
import argparse
import tensorflow as tf
import pandas as pd
import csv
from tensorflow.python.tools import freeze_graph
from tensorflow.python.tools import optimize_for_inference_lib
import numpy as np
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=100, type=int, help='batch size')
parser.add_argument('--train_steps', default=1000, type=int,
help='number of training steps')
features_global = None
feature_spec = None
MODEL_NAME = 'myModel'
def load_data(train_path, test_path):
"""Returns the iris dataset as (train_x, train_y), (test_x, test_y)."""
with open(train_path, newline='') as f:
reader = csv.reader(f)
column_names = next(reader)
y_name = column_names[-1]
train = pd.read_csv(train_path, names=column_names, header=0)
train_x, train_y = train, train.pop(y_name)
test = pd.read_csv(test_path, names=column_names, header=0)
test_x, test_y = test, test.pop(y_name)
return (train_x, train_y), (test_x, test_y)
def train_input_fn(features, labels, batch_size):
"""An input function for training"""
# Convert the inputs to a Dataset.
dataset = tf.data.Dataset.from_tensor_slices((dict(features), labels))
# Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(1000).repeat().batch(batch_size)
# Return the dataset.
return dataset
def eval_input_fn(features, labels, batch_size):
"""An input function for evaluation or prediction"""
features=dict(features)
if labels is None:
# No labels, use only features.
inputs = features
else:
inputs = (features, labels)
# Convert the inputs to a Dataset.
dataset = tf.data.Dataset.from_tensor_slices(inputs)
# Batch the examples
assert batch_size is not None, "batch_size must not be None"
dataset = dataset.batch(batch_size)
# Return the dataset.
return dataset
def main(argv):
args = parser.parse_args(argv[1:])
train_path = "trainData.csv"
test_path = "testData.csv"
# Fetch the data
(train_x, train_y), (test_x, test_y) = load_data(train_path, test_path)
# Load labels
num_labels = 5
# Feature columns describe how to use the input.
my_feature_columns = []
for key in train_x.keys():
my_feature_columns.append(tf.feature_column.numeric_column(key=key))
# Build 2 hidden layer DNN
classifier = tf.estimator.DNNClassifier(
feature_columns=my_feature_columns,
hidden_units=[100, 500],
optimizer=tf.train.AdagradOptimizer(learning_rate=0.003),
# The model must choose between 'num_labels' classes.
n_classes=num_labels,
model_dir="myModel")
# Train the Model
classifier.train(
input_fn=lambda:train_input_fn(train_x, train_y,
args.batch_size),
steps=args.train_steps)
# Evaluate the model.
eval_result = classifier.evaluate(
input_fn=lambda:eval_input_fn(test_x, test_y,
args.batch_size))
print('\nTest set accuracy: {accuracy:0.3f}\n'.format(**eval_result))
# Export model
feature_spec = tf.feature_column.make_parse_example_spec(my_feature_columns)
serve_input_fun = tf.estimator.export.build_parsing_serving_input_receiver_fn(feature_spec)
saved_model_path = classifier.export_savedmodel(
export_dir_base="out",
serving_input_receiver_fn=serve_input_fun,
as_text=True,
checkpoint_path=classifier.latest_checkpoint(),
)
tf.reset_default_graph()
var = tf.Variable(0)
with tf.Session() as sess:
# First let's load meta graph and restore weights
sess.run(tf.global_variables_initializer())
latest_checkpoint_path = classifier.latest_checkpoint()
saver = tf.train.import_meta_graph(latest_checkpoint_path + '.meta')
saver.restore(sess, latest_checkpoint_path)
input_arrays = ["dnn/input_from_feature_columns/input_layer/concat"]
output_arrays = ["dnn/logits/BiasAdd"]
frozen_graph_def = tf.graph_util.convert_variables_to_constants(
sess, sess.graph_def,
output_node_names=["dnn/logits/BiasAdd"])
frozen_graph = "out/frozen_graph.pb"
with tf.gfile.FastGFile(frozen_graph, "wb") as f:
f.write(frozen_graph_def.SerializeToString())
# save original graphdef to text file
with open("estimator_graph.pbtxt", "w") as fp:
fp.write(str(sess.graph_def))
# save frozen graph def to text file
with open("estimator_frozen_graph.pbtxt", "w") as fp:
fp.write(str(frozen_graph_def))
input_node_names = input_arrays
output_node_name = output_arrays
output_graph_def = optimize_for_inference_lib.optimize_for_inference(
frozen_graph_def, input_node_names, output_node_name,
tf.float32.as_datatype_enum)
final_model_path = 'out/opt_' + MODEL_NAME + '.pb'
with tf.gfile.FastGFile(final_model_path, "wb") as f:
f.write(output_graph_def.SerializeToString())
tflite_file = "out/iris.tflite"
converter = tf.contrib.lite.TocoConverter.from_frozen_graph(final_model_path, input_arrays, output_arrays, input_shapes={"dnn/input_from_feature_columns/input_layer/concat": [1, 10]})
tflite_model = converter.convert()
open(tflite_file, "wb").write(tflite_model)
interpreter = tf.contrib.lite.Interpreter(model_path=tflite_file)
interpreter.allocate_tensors()
# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
# Test model on random input data.
input_shape = input_details[0]['shape']
# change the following line to feed into your own data.
input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
resultlist = list()
df = pd.read_csv(test_path)
expected = df.iloc[:, -1].values.tolist()
with open(test_path, newline='') as f:
reader = csv.reader(f)
column_names = next(reader)
for x in range(0, len(expected)):
linea = next(reader)
linea = linea[:len(linea) - 1]
input_data2 = np.array(linea, dtype=np.float32)
interpreter.set_tensor(input_details[0]['index'], [input_data2])
interpreter.invoke()
output_data = interpreter.get_tensor(output_details[0]['index'])
#print(output_data)
max = 0;
longitud = len(output_data[0])
for k in range(0, longitud):
if (output_data[0][k] > output_data[0][max]):
max = k
resultlist.append(max)
print(resultlist)
coincidences = 0
for pred_dict, expec in zip(resultlist, expected):
if pred_dict == expec:
coincidences = coincidences + 1
print("tflite Accuracy: " + str(coincidences / len(expected)))
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
tf.app.run(main)
我希望你们中的一些人可以识别错误，或者给出可能的解决方案
答案 0 :(得分：0)
我遇到了同样的问题。在我看来，精度问题主要是由于未能检测到重叠物体而引起的。但是我无法弄清楚代码的哪一部分是错误的。
答案 1 :(得分：-1)
此问题已在此处回答，请检查一下可能有帮助：
https://stackoverflow.com/a/58583602/11517841
如答案分享中所述，做一些
如果图像上的预处理
首先是问题，则可以解决该问题。
要对此进行详细说明，请参见共享链接的引号：
下面看到的代码是我所说的预处理：
test_image=cv2.imread(file_name)
test_image=cv2.resize(test_image,(299,299),cv2.INTER_AREA)
test_image= np.expand_dims((test_image)/255,axis=0).astype(np.float32)
interpreter.set_tensor(input_tensor_index, test_image)
interpreter.invoke() digit = np.argmax(output()[0])
#print(digit)
prediction=result[digit]如您所见，有两个关键的命令/预处理已完成 使用“ imread（）”读取图像后：
i）图像的大小应调整为“ input_height”的大小 和使用的输入图像/张量的“ input_width”值 在训练中。就我而言（inception-v3）这两个都是299 “ input_height”和“ input_width”。 （阅读该模型的文档 为此值或在您以前用来在文件中查找此变量 训练或再训练模型）
ii）上面代码中的下一个命令是：
test_image = np.expand_dims((test_image)/255,axis=0).astype(np.float32)我是从“公式” /模型代码中得到的：
test_image=np.expand_dims((test_imageinput_mean)/input_std,axis=0).astype(np.float32)阅读文档后发现，对于我的体系结构，input_mean = 0，input_std = 255。
希望这会有所帮助。