[英]Incompatible dense layer error in keras
我輸入的是一系列視頻,數量為8500。 每個視頻作為一系列50幀饋送到LSTM,每個幀具有960像素。 因此,輸入dim為8500,50,960,有487種可能的輸出類別,因此輸出尺寸為8500,487。
但是,當我運行以下代碼時,我在keras中遇到了這些錯誤。
任何幫助是極大的贊賞。 謝謝!
(8500,50,960)
(8500,487)
創建模型
添加第一層
添加第二層
添加輸出層
追溯(最近一次通話):
在model.add(Dense(487,activation ='softmax'))中的文件“ /Users/temp/PycharmProjects/detect_sport_video/build_model.py”,第68行
添加文件output / tensor = layer(self.outputs)的文件“ /Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/models.py”,行146 [0])
調用 self.assert_input_compatibility(x)中的文件“ /Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/engine/topology.py”第441行)
在assert_input_compatibility str(K.ndim中,文件“ /Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/engine/topology.py”,第382行(X)))
例外:輸入0與層密_1不兼容:預期ndim = 2,找到的ndim = 3
from keras.models import Sequential
from keras.layers import LSTM, Dense
import numpy as np
from PIL import Image
import os
def atoi(video):
return int(video) if video.isdigit() else video
def natural_keys(video):
return [ atoi(c) for c in os.path.splitext(video) ]
input_data =np.zeros((8500,50,960))
video_index = 0
data = 'train'
video_list = sorted(os.listdir('/Users/temp/PycharmProjects/detect_sport_video/' + data + '_frame_resize1/'))
video_list.sort(key=natural_keys)
for video in video_list:
if video != '.DS_Store':
frame_index = 0
frame_list = sorted(os.listdir('/Users/temp/PycharmProjects/detect_sport_video/' + data + '_frame_resize1/' + video + '/'))
frame_list.sort(key=natural_keys)
for frame in frame_list:
image = np.asarray(Image.open('/Users/temp/PycharmProjects/detect_sport_video/' + data + '_frame_resize1/' + video + '/' + frame))
image = image.reshape(image.shape[0] * image.shape[1],3)
image = (image[:,0] + image[:,1] + image[:,2]) / 3
image = image.reshape(len(image),1)
image = image[:960]
image = image.T
input_data[video_index][frame_index] = image
frame_index += 1
video_index += 1
print input_data.shape
cnt = 1
output_classes = []
with open('/Users/temp/PycharmProjects/detect_sport_video/sports-1m-dataset/' + data + '_correct_links.txt') as input_file:
while cnt <= 8500:
output_classes.append(int(input_file.readline().split()[2]))
cnt += 1
output_data =np.zeros((8500,487))
output_index = 0
while(output_index < 8500):
output_data[output_index,output_classes[output_index]] = 1
output_index += 1
print output_data.shape
print("Creating model..")
model = Sequential()
print("Adding first layer..")
model.add(LSTM(100, return_sequences=True,
input_shape=(50, 960)))
print("Adding second layer..")
model.add(LSTM(100, return_sequences=True))
print("Adding output layer..")
model.add(Dense(487, activation='softmax'))
print "Compiling model.."
model.compile(loss='categorical_crossentropy',
optimizer='RMSprop',
metrics=['accuracy'])
print "Fitting model.."
model.fit(input_data,output_data,
batch_size=50, nb_epoch=100)
另外,如果我在添加每個LSTM層后嘗試打印model.output_shape,則得到的輸出為(None,50,200),但應該為(None,200)。 那就是問題所在。 但我不知道為什么要得到(無,50,200)。 有任何想法嗎?
print(“添加第二層。”)model.add(LSTM(100,return_sequences = False))
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.