CODEWITHSUNDEEP
tensorflowmachine-learningdeep-learningdatasetconv-neural-network
Baburam Chaudhary
Baburam Chaudhary

Reputation: 11

custom dataset for image in tensorflow 2.0

I am trying to "custom dataset for image" using tensorflow 2.0 my directory structure is: say (PetImage)as root directory which contains two classes: Cat and Dog which contains respective images. /PetImage| |Cat | img1.jpg | img2.jpg | imgn.jpg | ...

    |Dog | img1.jpg
         | img2.jpg
         | ig3.jpg
         | ig.jpg
         | ...

My code is as follows: img_height = 64 img_width = 64

ds_train = tf.keras.preprocessing.image_dataset_from_directory( "I:\Image\Data\kagglecatsanddogs_5340\PetImages", labels="inferred", label_mode="int", color_mode="rgb", image_size=(img_height, img_width), shuffle=True, seed=123, validation_split=0.3, subset="training", interpolation="bicubic" )

history = model.fit(ds_train, epochs=2)

Error:

InvalidArgumentError: Graph execution error:

Input is empty. [[{{node decode_image/DecodeImage}}]] [[IteratorGetNext]] [Op:__inference_train_function_1704]

Upvotes: 0

Views: 80

Answers (1)

otaku
otaku

Reputation: 86

In tensorflow 2.0, there is no function - tf.keras.preprocessing.image_dataset_from_directory() and even in the latest version of tensorflow 2.11 there is a function tf.keras.utils.image_dataset_from_directory()

Refer to this link - "https://www.tensorflow.org/api_docs/python/tf/keras/utils/image_dataset_from_directory"

Upvotes: 0

Related Questions