ValueError Traceback (the most recent call last) 
 () 
23 BATCH_SIZE, 
24 CAPACITY) 
---> 25 train_logits=model. Inference (train_batch BATCH_SIZE, N_CLASSES) 
26 train_loss=model. Losses (train_logits train_label_batch) 
27 train_op=model. Trainning (train_loss learning_rate) 

E: \ cat and dog \ model py in inference (images, batch_size n_classes) 
8 shape=[16] 3, 3, 3,, 
9 dtype=tf float32, 
---> 10, initializer=tf. Truncated_normal_initializer (stddev=0.1, dtype=tf. Float32)) 
11 biases=tf. Get_variable (' biases, 
12 shape=[16], 

D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ ops \ variable_scope py in get_variable (name, shape, dtype, initializer, regularizer, trainable, collections, caching_device, partitioner, validate_shape, custom_getter) 
1022 collections=collections, caching_device=caching_device, 
1023 partitioner=partitioner, validate_shape=validate_shape, 
-> 1024 custom_getter=custom_getter) 
1025 
1026 

D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ ops \ variable_scope py in get_variable (self, var_store, name, shape, dtype,, initializer, regularizer, trainable, collections, caching_device, partitioner, validate_shape, custom_getter) 
848 collections=collections, caching_device=caching_device, 
849 partitioner=partitioner, validate_shape=validate_shape, 
- & gt; 850 custom_getter=custom_getter) 
851 
852 def _get_partitioned_variable (self, 

D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ ops \ variable_scope py in get_variable (self, the name, shape, dtype, initializer, regularizer, reuse, trainable, collections, caching_device, partitioner, validate_shape, custom_getter) 
344 reuse=reuse, trainable=trainable, collections=collections, 
345 caching_device=caching_device partitioner=partitioner, 
- & gt; 346 validate_shape=validate_shape) 
347 
348 def _get_partitioned_variable (

D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ ops \ variable_scope py in _true_getter (name, shape, dtype, initializer, regularizer, reuse, trainable, collections, caching_device, partitioner, validate_shape) 
329, initializer=, initializer, regularizer=regularizer, reuse=reuse, 
330 trainable=trainable, collections=collections, 
- & gt; 331 caching_device=caching_device validate_shape=validate_shape) 
332 
333 if custom_getter is not None: 

D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ ops \ variable_scope py in _get_single_variable (self, the name, shape, dtype, initializer, regularizer, partition_info, reuse, trainable, collections, caching_device, validate_shape) 
630 "Did you mean to set reuse=True in VarScope? "
631 "Originally defined at: \ n \ n % s" % (
- & gt; 632 the name, "". Join (traceback format_list (TB)))) 
633 found_var=self. _vars [name] 
634 if not shape. Is_compatible_with (found_var get_shape ()) : 

ValueError: Variable conv1/weights already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at: 

The File "D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ framework \ ops py", line 1128, in __init__ 
Self. _traceback=_extract_stack () 
The File "D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ framework \ ops py", line 2240, in create_op 
Original_op=self. _default_original_op op_def=op_def) 
The File "D: \ Anaconda \ lib \ site - packages \ tensorflow \ python \ framework \ op_def_library py", line 759, in apply_op 
Op_def=op_def) 

Training dogs and cats war training set when the above problems, don't understand, ask the great spirit

CodePudding user response:

Model. Inference (train_batch BATCH_SIZE, N_CLASSES) this should be inside with tf. Variable_scope (' layer1) : this code, instead of with tf. Variable_scope (' layer1 'reuse=reuse) : the second parameter of True

CodePudding user response:

Add this code at the front: tf reset_default_graph ()

CodePudding user response:

Model. Inference (train_batch BATCH_SIZE, N_CLASSES) this should be inside with tf. Variable_scope (' layer1) : this code, instead of with tf. Variable_scope (' layer1, reuse=tf AUTO_REUSE) :

CodePudding user response:

Method is very good, perfect solve the problem, kiss

CodePudding user response:

Hello, I want to ask about the model. The inference (train_batch BATCH_SIZE, N_CLASSES) where the ah, rookie will not find,,,, cry fainted

CodePudding user response:

"Model. The inference" generation means you build neural network model of the piece of script

CodePudding user response:

null