niektemme / tensorflow-mnist-predict Goto Github PK

Hi, thanks you for sharing. I ran the code. It gives me an error

local variable 'nheigth' referenced before assignment

I run it by using:
(tensorflow)xu@xu-ThinkCentre-M72e:~ $ python Predict.py 'HandWrittenDigit2.png'
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcurand.so locally
Traceback (most recent call last):
File "Predict.py", line 134, in
main(sys.argv[1])
File "Predict.py", line 129, in main
imvalue = imageprepare(argv)
File "Predict.py", line 100, in imageprepare
if (nheigth == 0): #rare case but minimum is 1 pixel
UnboundLocalError: local variable 'nheigth' referenced before assignment
(tensorflow)xu@xu-ThinkCentre-M72e:~ $ python Predict.py 'HandWrittenDigit2.png'
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcurand.so locally
Traceback (most recent call last):
File "Predict.py", line 133, in
main(sys.argv[1])
File "Predict.py", line 128, in main
imvalue = imageprepare(argv)
File "Predict.py", line 99, in imageprepare
if (nheigth == 0): #rare case but minimum is 1 pixel
UnboundLocalError: local variable 'nheigth' referenced before assignment
(tensorflow)xu@xu-ThinkCentre-M72e:~ $

Your work helps me, but i think the variable name "nheigth" is wrong , it should be "nheight". You can find it in line 76/77 of predict_1.py and line 116/117 of predict_2.py.

(working on predict_2.py)

How can I give multiple images at once ?
How can I visualize the final result of this in console ?
How can I print/save the multiple digits in a file (example .txt) ?

this is code:
def predictint(imvalue):

     with tf.Graph().as_default():
      def addlayer(input_data,insize,outsize,act_function=None):
            W=tf.Variable(tf.random_normal([insize,outsize]))
            b=tf.Variable(tf.zeros([outsize]))+0.1
            out_data=tf.matmul(input_data,W)+b
            if act_function==None:
	         return out_data
            elif act_function=="relu":
	         return tf.nn.relu(out_data)
            elif act_function=="softmax":
	          return tf.nn.softmax(out_data)
           else:
	          return tf.nn.sigmoid(out_data)
           x_input=tf.placeholder(tf.float32,[None,784])
          #y_input=tf.placeholder(tf.float32,[None,10])
           l1=addlayer(x_input,784,64,act_function="relu")
           l2=addlayer(l1,64,10,act_function="softmax")	    
          init_op = tf.initialize_all_variables()
          saver = tf.train.Saver()	    
    
              with tf.Session() as sess:
	         sess.run(init_op)
	         saver.restore(sess, "./model.ckpt")
                 prediction=tf.argmax(l2,1)
	         return prediction.eval(feed_dict={x_input: [imvalue]}, session=sess)

I'm using Mac 10.13.3 Python 3.6.2 and i just installed tensorflow via pip.And i also installed relevant dependencies using pip.But when i ran the create_model_1.py some strange error happened. Below is the problems .Hope someone can help.

Hello there,

I am getting this error :
ValueError : Parent directory of model.ckpt doesn't exist, can't save.

With regards

Hello,

I'm trying your scripts, but i can predict any numbers because when i run create_model1 or create_model2. They finish because they can't save the model.
Here the error code :

Traceback (most recent call last):
File "create_model_1.py", line 61, in <module>
save_path = saver.save(sess, "model1.ckpt"')
File "C:\Users\Laura\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\training\saver.py", line 1365, in save
"Parent directory of {} doesn't exist, can't save.".format(save_path))
ValueError: Parent directory of model1.ckpt doesn't exist, can't save.

Thanks.
Jordan

I use spyder for run create_model_2.py and then used the predict_2. but it's get error with restore.
I closed spyder and run predict_2 , this time it is run correct but then i want to run it make error with restore again I closed spyder and open it and it run correct.
what is the problem?