ValueError: Could not find matching concrete function to call loaded from the SavedModel

Question

I am trying to build a model for crop identification and keep getting this error:

import tensorflow as tf
import tensorflow_hub as hub
 
#Read crop details
import pandas as pd
crop_details_csv =  pd.read_excel('/content/drive/MyDrive/Crop Identification/Crop_details.xlsx')
crop_details_csv.head()
 
#Get imamges filepaths
filename  = ['drive/MyDrive/Crop Identification/Train2/' + fname for fname in crop_details_csv['path']]
 
import numpy as np
labels = crop_details_csv['croplabel']
labels=np.array(labels)
#if len(labels)==len(filename):
  #print('Yes')
#else:
  #print('NO')  
unique_labels = np.unique(labels)  
unique_labels
 
boolean_labels = [label == unique_labels for label in labels]#turn labels to numbers
 
#Split our data and creating Validation set
x = filename
y = boolean_labels
 
#Get validation set
from sklearn.model_selection import train_test_split
x_train,x_val,y_train,y_val=train_test_split(x,y,test_size=0.2,random_state=42)
 
#Turn Images to tensors
image_size=224
 
def preprocess_image(image_path,image_size=image_size):
  #read an image file
  image= tf.io.read_file(image_path)
  #turn image into numerical tensors with RGB
  image = tf.image.decode_jpeg(image,channels=3)
  #convert color values from 0-255 to 0-1 #Normaliization
  image = tf.image.convert_image_dtype(image,tf.float32)
  #resize image to 224,224
  image = tf.image.resize(image,size=[image_size,image_size])
 
  return image
 
  #Turn Data into batches
#Returns tuple (image,label)
def get_image_label(image_path,label):
  image = preprocess_image(image_path)
  return image,label
 
Batch_size=32
def create_batches(x,y=None,batch_size=Batch_size,valid_data=False,test_data=False):
  if test_data:#test data has no labels
    data= tf.data.Dataset.from_tensor_slices((tf.constant(x)))#no labels
    data_batch = data.map(preprocess_image).batch(Batch_size)
    return data_batch
  elif valid_data:#no shuffling for valid data
     data= tf.data.Dataset.from_tensor_slices((tf.constant(x),(tf.constant(y))))
     data_batch = data.map(get_image_label).batch(Batch_size)
     return data_batch
  else:
    data= tf.data.Dataset.from_tensor_slices((tf.constant(x),(tf.constant(y))))
    data= data.shuffle(buffer_size=len(x))#shuffle for training data
    data= data.map(get_image_label)
    data_batch=data.batch(Batch_size)
 
  return data_batch
 
train_data=create_batches(x_train,y_train)
val_data=create_batches(x_val,y_val,valid_data=True)
 
input_shape=[None,image_size,image_size,3]#batch ,height ,width , color channels
output_shape= len(unique_labels)
model_URL = "https://tfhub.dev/google/imagenet/mobilenet_v2_035_128/classification/5"
 
def create_model(input_shape=input_shape,output_shape=output_shape,model_URL=model_URL):
  #model layers setup
  model = tf.keras.Sequential([hub.KerasLayer(model_URL),#input layer
                               tf.keras.layers.Dense(units=output_shape,activation='softmax')])#output layer
  #compile model
  model.compile(loss=tf.keras.losses.CategoricalCrossentropy(),
                optimizer=tf.keras.optimizers.Adam(),
                metrics=['accuracy'])
  #Build model
  model.build(input_shape)
 
  return model
 
  model = create_model()

----------------------------------------------------------------- 
----------
ValueError                                Traceback (most recent call last)
 in ()
----> 1 model = create_model()
      2 model.summary()

5 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/autograph/impl/api.py in wrapper(*args, **kwargs)
    697       except Exception as e:  # pylint:disable=broad-except
    698         if hasattr(e, 'ag_error_metadata'):
--> 699           raise e.ag_error_metadata.to_exception(e)
    700         else:
    701           raise

ValueError: Exception encountered when calling layer "keras_layer" (type KerasLayer).

in user code:

    File "/usr/local/lib/python3.7/dist-packages/tensorflow_hub/keras_layer.py", line 237, in call  *
        result = smart_cond.smart_cond(training,

    ValueError: Could not find matching concrete function to call loaded from the SavedModel. Got:
      Positional arguments (4 total):
        * Tensor("inputs:0", shape=(224, 224, 3), dtype=float32)
        * False
        * False
        * 0.99
      Keyword arguments: {}
    
     Expected these arguments to match one of the following 4 option(s):
    
    Option 1:
      Positional arguments (4 total):
        * TensorSpec(shape=(None, 128, 128, 3), dtype=tf.float32, name='inputs')
        * True
        * True
        * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
      Keyword arguments: {}
    
    Option 2:
      Positional arguments (4 total):
        * TensorSpec(shape=(None, 128, 128, 3), dtype=tf.float32, name='inputs')
        * True
        * False
        * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
      Keyword arguments: {}
    
    Option 3:
      Positional arguments (4 total):
        * TensorSpec(shape=(None, 128, 128, 3), dtype=tf.float32, name='inputs')
        * False
        * True
        * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
      Keyword arguments: {}
    
    Option 4:
      Positional arguments (4 total):
        * TensorSpec(shape=(None, 128, 128, 3), dtype=tf.float32, name='inputs')
        * False
        * False
        * TensorSpec(shape=(), dtype=tf.float32, name='batch_norm_momentum')
      Keyword arguments: {}


Call arguments received:
  • inputs=tf.Tensor(shape=(224, 224, 3), dtype=float32)
  • training=None

ValueError: Could not find matching concrete function to call loaded from the SavedModel

0 Answers