keras中不兼容的密集层错误 [英] Incompatible dense layer error in keras

问题描述

我输入的是一系列视频，数量为8500.每个视频作为一系列50帧被馈送到LSTM，每个帧具有960像素. 所以输入昏暗是8500,50,960 有487种可能的输出类别，因此输出尺寸为8500,487.

My input is an series of videos, 8500 in number. Each video is fed to LSTM as a series of 50 frames, each frame having 960 pixels. So the input dim is 8500,50,960 There are 487 possible output classes possible, so the output dimension is 8500,487.

但是当我运行以下代码时，我在keras中得到了这些错误.

But when I run the following code, I am getting these errors in keras.

任何帮助将不胜感激.谢谢！

Any help is greatly appreciated. Thanks!

(8500，50，960)

(8500, 50, 960)

(8500，487)

创建模型..

添加第一层.

添加第二层.

添加输出层.

回溯(最近通话最近一次):

Traceback (most recent call last):

文件"/Users/temp/PycharmProjects/detect_sport_video/build_model.py"，第68行，在 model.add(Dense(487，activation ='softmax'))

File "/Users/temp/PycharmProjects/detect_sport_video/build_model.py", line 68, in model.add(Dense(487, activation='softmax'))

添加文件"/Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/models.py"，第146行 output_tensor = layer(self.outputs [0])

File "/Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/models.py", line 146, in add output_tensor = layer(self.outputs[0])

文件"/Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/engine/topology.py"，第441行，位于致电 self.assert_input_compatibility(x)

File "/Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/engine/topology.py", line 441, in call self.assert_input_compatibility(x)

文件"/Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/engine/topology.py"，第382行，在assert_input_compatibility中 str(K.ndim(x)))

File "/Users/temp/anaconda/lib/python2.7/site-packages/Keras-1.0.3-py2.7.egg/keras/engine/topology.py", line 382, in assert_input_compatibility str(K.ndim(x)))

异常:输入0与层密_1不兼容:预期ndim = 2，发现ndim = 3

Exception: Input 0 is incompatible with layer dense_1: expected ndim=2, found 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)

此外，如果我在添加每个LSTM层后尝试打印model.output_shape，我得到的输出是(None，50，200)，但应该是(None，200).那就是问题所在.但是我不知道为什么要得到(无，50,200).有什么想法吗?

Also, If I try to print model.output_shape after adding every LSTM layer, the output I get is (None, 50, 200) but it should have been (None,200). Thats where the problem is. But I dont know why am getting (None,50,200). Any ideas?

推荐答案

print(添加第二层.") model.add(LSTM(100，return_sequences = False))

print("Adding second layer..") model.add(LSTM(100, return_sequences=False))

这篇关于keras中不兼容的密集层错误的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！