我正在尝试构建一个类似于 theanologistic_sgd.py 实现中提供的 mnist.pkl.gz 的数据集。以下是我的代码片段。
import numpy as np
import csv
from PIL import Image
import gzip, cPickle
import theano
from theano import tensor as T
def load_dir_data(csv_file=""):
print(" reading: %s" %csv_file)
dataset=[]
labels=[]
cr=csv.reader(open(csv_file,"rb"))
for row in cr:
print row[0], row[1]
try:
image=Image.open(row[0]+'.jpg').convert('LA')
pixels=[f[0] for f in list(image.getdata())]
dataset.append(pixels)
labels.append(row[1])
del image
except:
print("image not found")
ret_val=np.array(dataset,dtype=theano.config.floatX)
return ret_val,np.array(labels).astype(float)
def generate_pkl_file(csv_file=""):
Data, y =load_dir_data(csv_file)
train_set_x = Data[:1500]
val_set_x = Data[1501:1750]
test_set_x = Data[1751:1900]
train_set_y = y[:1500]
val_set_y = y[1501:1750]
test_set_y = y[1751:1900]
# Divided dataset into 3 parts. I had 2000 images.
train_set = train_set_x, train_set_y
val_set = val_set_x, val_set_y
test_set = test_set_x, val_set_y
dataset = [train_set, val_set, test_set]
f = gzip.open('file.pkl.gz','wb')
cPickle.dump(dataset, f, protocol=2)
f.close()
if __name__=='__main__':
generate_pkl_file("trainLabels.csv")
错误消息:回溯(最后一次调用):
File "convert_dataset_pkl_file.py", line 50, in <module>
generate_pkl_file("trainLabels.csv")
File "convert_dataset_pkl_file.py", line 29, in generate_pkl_file
Data, y =load_dir_data(csv_file)
File "convert_dataset_pkl_file.py", line 24, in load_dir_data
ret_val=np.array(dataset,dtype=theano.config.floatX)
ValueError: setting an array element with a sequence.
csv文件包含两个字段..图像名称,分类标签在python解释器中运行时,它似乎对我有用..如下..我没有得到错误说在这里设置一个带有序列的数组元素..
---------python解释器输出----------
image=Image.open('sample.jpg').convert('LA')
pixels=[f[0] for f in list(image.getdata())]
dataset=[]
dataset.append(pixels)
dataset.append(pixels)
dataset.append(pixels)
dataset.append(pixels)
dataset.append(pixels)
b=numpy.array(dataset,dtype=theano.config.floatX)
b
array([[ 2., 0., 0., ..., 0., 0., 0.],
[ 2., 0., 0., ..., 0., 0., 0.],
[ 2., 0., 0., ..., 0., 0., 0.],
[ 2., 0., 0., ..., 0., 0., 0.],
[ 2., 0., 0., ..., 0., 0., 0.]])
即使我正在运行相同的指令集(逻辑上),当我运行 sample.py 时,我得到 valueError: setting an array element with a sequence..我试图理解这种行为..任何帮助都会很棒..