InvalidArgumentError：形状[-1,150,150,1]具有负向尺寸

我正在开发一个CNN，通过使用基于Tensorflow的TFlearn对图像进行分类，并且我使用scipy.misc.imread读取图像，现在我将数据提供给我的模型，但发生意外错误。InvalidArgumentError：形状[-1,150,150,1]具有负向尺寸

这里是我的代码：

import numpy as np 
import os 
import tensorflow as tf 
from scipy import misc 
from PIL import Image 
import keras 


IMAGE_SIZE = 150 
image_path = "dragonfly" 


labels = np.zeros((4063, 2)) 
labels [0:2363] = (1, 0) 
labels [2364:4062] = (0, 1) 
test_labels = np.zeros((200, 2)) 
test_labels [0:99] = (1, 0) 
test_labels [100:199] = (0, 1) 


fset = [] 
fns=[os.path.join(root,fn) for root,dirs,files in os.walk(image_path) for fn in files] 
for f in fns: 
    fset.append(f) 

def create_train_data(): 
    train_data = [] 
    fns=[os.path.join(root,fn) for root,dirs,files in os.walk(image_path) for fn in files] 
    for f in fns: 
     image = misc.imread(f, mode = 'L') 
     image = misc.imresize(image, (IMAGE_SIZE, IMAGE_SIZE)) 
     train_data.append(np.array(image)) 
    return train_data 


train_data = create_train_data() 
print (len(train_data)) 

training_data = train_data[0:2264] + train_data[2364:3963] 
train_labels = np.concatenate((labels[0:2264], labels[2364:3963])) 
test_data = train_data[2264:2364] + train_data[3963:4063] 


import tflearn 
from tflearn.layers.conv import conv_2d, max_pool_2d 
from tflearn.layers.core import input_data, dropout, fully_connected 
from tflearn.layers.estimator import regression 

convnet = input_data(shape=[None, IMAGE_SIZE, IMAGE_SIZE, 1], name='input') 

convnet = conv_2d(convnet, 32, 5, activation='relu') 
convnet = max_pool_2d(convnet, 5) 

convnet = conv_2d(convnet, 64, 5, activation='relu') 
convnet = max_pool_2d(convnet, 5) 

convnet = fully_connected(convnet, 1024, activation='relu') 
convnet = dropout(convnet, 0.8) 

convnet = fully_connected(convnet, 2, activation='softmax') 
convnet = regression(convnet, optimizer='adam', learning_rate=1e-3, loss='categorical_crossentropy', name='targets') 

model = tflearn.DNN(convnet, tensorboard_dir='log') 

X = np.asarray(training_data).reshape(3863, IMAGE_SIZE, IMAGE_SIZE, 1) 
Y = [i for i in train_labels] 

test_x = np.asarray(test_data).reshape(200, IMAGE_SIZE, IMAGE_SIZE, 1) 
test_y = [i for i in test_labels] 

model.fit({'input': X}, {'targets': train_labels}, n_epoch=2, validation_set=({'input': test_x}, {'targets': test_labels}), 
    snapshot_step=200, show_metric=True)

错误：

InvalidArgumentError: Shape [-1,150,150,1] has negative dimensions

来源

2017-08-12 Enoch Yang

请问您可以发布完整的追溯？ – ml4294

@ ml4294其实回溯很长，我认为最有价值的部分是：InvalidArgumentError：形状[-1,150,150,1]具有负向尺寸 \t [[Node：input_1/X = Placeholder [dtype = DT_FLOAT，shape = [？，150,150,1]，_device =“/作业：本地主机/副本：0 /任务：0/gpu：0”]（）]] –

这将有助于。

model.fit(feed_dicts={input: X, targets: train_labels}, n_epoch=2, val_feed_dicts={input: test_x, targets: test_labels}, 
snapshot_step=200, show_metric=True)

来源

2017-08-12 08:53:51

是的，我实际上传递nd数组模型，请参阅X和test_x在我的代码 –

哦！我错过了，看到我的编辑 –

InvalidArgumentError：形状[-1,150,150,1]具有负向尺寸

回答

相关问题