Jon*_*nah 5 python sequence-generators keras tensorflow
我根据链接的指导实现了一个序列生成器对象。
import tensorflow as tf
from cv2 import imread, resize
from sklearn.utils import shuffle
from cv2 import imread, resize
import numpy as np
from tensorflow.keras import utils
import math
import keras as ks
class reader(tf.keras.utils.Sequence):
def __init__(self, x, y, batch_size, n_class):
self.x, self.y = x, y
self.batch_size = batch_size
self.n_class = n_class
def __len__(self):
return math.ceil(len(self.x) / self.batch_size)
def __getitem__(self, idx):
print('getitem', idx)
batch_x = self.x[idx * self.batch_size:(idx + 1) *
self.batch_size]
batch_y = self.y[idx * self.batch_size:(idx + 1) *
self.batch_size]
data_x = list()
for batch in batch_x:
tmp = list()
for img_path in batch:
try:
img = imread(img_path)
tmp.append(img)
except Exception as e:
print(e)
print('failed to find path {}'.format(img_path))
data_x.append(tmp)
#
data_x = np.array(data_x, dtype='object')
data_y = np.array(batch_y)
data_y = utils.to_categorical(data_y, self.n_class)
print('return item')
print(data_x.shape)
return (data_x, data_y)
def on_epoch_end(self):
# option method to run some logic at the end of each epoch: e.g. reshuffling
print('on epoch end')
seed = np.random.randint()
self.x = shuffle(self.x, random_state=seed)
self.y = shuffle(self.y, random_state=seed)
但是，它不适用于tensorflow模型的fit api。下面是我用来复制这个问题的简单模型架构。
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv3D(10, input_shape=(TEMPORAL_LENGTH,HEIGHT,WIDTH,CHANNEL), kernel_size=(2,2,2), strides=2))
model.add(tf.keras.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(tf.keras.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(tf.keras.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(10))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy', tf.keras.metrics.Precision(), tf.keras.metrics.Recall()])
model.summary()
让我创建一个阅读器
r1 = reader(x_train, y_train, 20, 10)
然后我调用 model.fit api。
train_history = model.fit(r1, epochs=3, steps_per_epoch=5, verbose=1)
### output ###
getitem 0
return item
(20, 16, 192, 256, 3)
WARNING:tensorflow:sample_weight modes were coerced from
...
to
['...']
Train for 5 steps
Epoch 1/3
如果我不打扰的话，就会永远这样。出于好奇，我使用 Keras api 创建的模型尝试了这种方法，令我惊讶的是它竟然有效！
model = ks.models.Sequential()
model.add(ks.layers.Conv3D(10, input_shape=(TEMPORAL_LENGTH,HEIGHT,WIDTH,CHANNEL), kernel_size=(2,2,2), strides=2))
model.add(ks.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(ks.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(ks.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(ks.layers.Flatten())
model.add(ks.layers.Dense(10))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
train_history = model.fit(r1, epochs=3, steps_per_epoch=5, verbose=1)
### output ###
Epoch 1/3
getitem 586
return item
(20, 16, 192, 256, 3)
getitem 169
1/5 [=====>........................] - ETA: 22s - loss: 11.0373 - accuracy: 0.0000e+00return item
(20, 16, 192, 256, 3)
getitem 601
2/5 [===========>..................] - ETA: 12s - loss: 7.9983 - accuracy: 0.0250 return item
(20, 16, 192, 256, 3)
getitem 426
3/5 [=================>............] - ETA: 8s - loss: 10.7049 - accuracy: 0.2500return item
(20, 16, 192, 256, 3)
getitem 243
4/5 [=======================>......] - ETA: 3s - loss: 8.5093 - accuracy: 0.1875
依赖关系
前辈。对于这么晚的回复，我深表歉意。我已经找到了这个问题的解决方法。我需要更改的只是在函数 self 处将 data_x 转换为 dtype='float32' 。获取项目（）。要复制该问题，只需将 dtype 更改为“对象”即可。
除此之外，请允许我分享一下ActionDataGenerator 类是根据Anujshah 的教程修改的。
import tensorflow as tf
from sklearn.utils import shuffle
import cv2
from cv2 import imread, resize
from tensorflow.keras import utils
import math
import keras as ks
import pandas as pd
import numpy as np
import os
from collections import deque
import copy
class reader(tf.keras.utils.Sequence):
def __init__(self, x, y, batch_size, n_class):
self.x, self.y = x, y
self.batch_size = batch_size
self.n_class = n_class
def __len__(self):
return math.ceil(len(self.x) / self.batch_size)
def __getitem__(self, idx):
batch_x = self.x[idx * self.batch_size:(idx + 1) *
self.batch_size]
batch_y = self.y[idx * self.batch_size:(idx + 1) *
self.batch_size]
data_x = list()
for batch in batch_x:
tmp = list()
for img_path in batch:
try:
img = imread(img_path)
if img.shape != (192, 256, 3):
img = cv2.resize(img,(256, 192))
tmp.append(img)
except Exception as e:
print(e)
print('failed to find path {}'.format(img_path))
data_x.append(tmp)
#
data_x = np.array(data_x, dtype='float32')
data_y = np.array(batch_y)
data_y = utils.to_categorical(data_y, self.n_class)
return data_x, data_y
def on_epoch_end(self):
# option method to run some logic at the end of each epoch: e.g. reshuffling
seed = np.random.randint()
self.x = shuffle(self.x, random_state=seed)
self.y = shuffle(self.y, random_state=seed)
class ActionDataGenerator(object):
def __init__(self,root_data_path,temporal_stride=1,temporal_length=16,resize=224, max_sample=20):
self.root_data_path = root_data_path
self.temporal_length = temporal_length
self.temporal_stride = temporal_stride
self.resize=resize
self.max_sample=max_sample
def file_generator(self,data_path,data_files):
'''
data_files - list of csv files to be read.
'''
for f in data_files:
tmp_df = pd.read_csv(os.path.join(data_path,f))
label_list = list(tmp_df['Label'])
total_images = len(label_list)
if total_images>=self.temporal_length:
num_samples = int((total_images-self.temporal_length)/self.temporal_stride)+1
img_list = list(tmp_df['FileName'])
else:
print ('num of frames is less than temporal length; hence discarding this file-{}'.format(f))
continue
samples = deque()
samp_count=0
for img in img_list:
if samp_count == self.max_sample:
break
samples.append(img)
if len(samples)==self.temporal_length:
samples_c=copy.deepcopy(samples)
samp_count+=1
for t in range(self.temporal_stride):
samples.popleft()
yield samples_c,label_list[0]
def load_samples(self,data_cat='train', test_ratio=0.1):
data_path = os.path.join(self.root_data_path,data_cat)
csv_data_files = os.listdir(data_path)
file_gen = self.file_generator(data_path,csv_data_files)
iterator = True
data_list = []
while iterator:
try:
x,y = next(file_gen)
x=list(x)
data_list.append([x,y])
except Exception as e:
print ('the exception: ',e)
iterator = False
print ('end of data generator')
# data_list = self.shuffle_data(data_list)
return data_list
def train_validation_split(self, data_list, target_column, val_size=0.1, ks_sequence=False):
dataframe = pd.DataFrame(data_list)
dataframe.columns = ['Feature', target_column]
data_dict = dict()
for i in range(len(np.unique(dataframe[target_column]))):
data_dict[i] = dataframe[dataframe[target_column]==i]
train, validation = pd.DataFrame(), pd.DataFrame()
for df in data_dict.values():
cut = int(df.shape[0] * val_size)
val = df[:cut]
rem = df[cut:]
train = train.append(rem, ignore_index=True)
validation = validation.append(val, ignore_index=True)
if ks_sequence:
return train['Feature'].values.tolist(), train['Label'].values.tolist(), \
validation['Feature'].values.tolist(), validation['Label'].values.tolist() # without shuffle
return train.values.tolist(), validation.values.tolist() # without shuffle
root_data_path = 'C:\\Users\\AI-lab\\Documents\\activity_file\\UCF101\\csv_files\\' # machine specific
CLASSES = 101
BATCH_SIZE = 10
EPOCHS = 1
TEMPORAL_STRIDE = 8
TEMPORAL_LENGTH = 16
MAX_SAMPLE = 20
HEIGHT = 192
WIDTH = 256
CHANNEL = 3
data_gen_obj = ActionDataGenerator(root_data_path, temporal_stride=TEMPORAL_STRIDE, \
temporal_length=TEMPORAL_LENGTH, max_sample=MAX_SAMPLE)
train_data = data_gen_obj.load_samples(data_cat='train')
x_train, y_train, x_val, y_val = data_gen_obj.train_validation_split(train_data, 'Label', 0.1, True)
r1 = reader(x_train, y_train, BATCH_SIZE, CLASSES)
r2 = reader(x_val, y_val, BATCH_SIZE, CLASSES)
print(type(r1), type(r2))
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Conv3D(10, input_shape=(TEMPORAL_LENGTH,HEIGHT,WIDTH,CHANNEL), kernel_size=(2,2,2), strides=2))
model.add(tf.keras.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(tf.keras.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(tf.keras.layers.Conv3D(10, kernel_size=(2,3,3), strides=2))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(101, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
train_history = model.fit(r1, epochs=3, steps_per_epoch=r1.__len__(), verbose=1)
score = model.evaluate(r2, steps=5)
print(score)
the exception:
end of data generator
<class '__main__.reader'> <class '__main__.reader'>
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv3d (Conv3D) (None, 8, 96, 128, 10) 250
_________________________________________________________________
conv3d_1 (Conv3D) (None, 4, 47, 63, 10) 1810
_________________________________________________________________
conv3d_2 (Conv3D) (None, 2, 23, 31, 10) 1810
_________________________________________________________________
conv3d_3 (Conv3D) (None, 1, 11, 15, 10) 1810
_________________________________________________________________
flatten (Flatten) (None, 1650) 0
_________________________________________________________________
dense (Dense) (None, 101) 166751
=================================================================
Total params: 172,431
Trainable params: 172,431
Non-trainable params: 0
_________________________________________________________________
WARNING:tensorflow:sample_weight modes were coerced from
...
to
['...']
Train for 17562 steps
Epoch 1/3
77/17562 [..............................] - ETA: 1:35:53 - loss: 67.0937 - accuracy: 0.0156