TypeError: Value passed to parameter 'input' has DataType bool not in list of allowed values: float32, float64, int32, uint8, int16, int8

Question

I have a dataset with 5 labels

def get_label(file_path):
  # convert the path to a list of path components
  parts = tf.strings.split(file_path, os.path.sep)
  class_names = ['daisy' 'dandelion' 'roses' 'sunflowers' 'tulips']
  # The second to last is the class-directory
  one_hot = parts[-2] == class_names
  # Integer encode the label
  return tf.argmax(one_hot)

def decode_img(img):
  # convert the compressed string to a 3D uint8 tensor
  img = tf.image.decode_jpeg(img, channels=3)
  # resize the image to the desired size
  return tf.image.resize(img, [img_height, img_width])

def process_path(file_path):
  label = get_label(file_path)
  # load the raw data from the file as a string
  img = tf.io.read_file(file_path)
  img = decode_img(img)
  return img, label

train_ds = train_ds.map(process_path, num_parallel_calls=AUTOTUNE)

If I change this code with other dataset having 2 labels, class_names = ['dog', 'cat'] I find this error TypeError: Value passed to parameter 'input' has DataType bool not in list of allowed values: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, uint16, complex128, float16, uint32, uint64 So how I can update def get_label(file_path)

rezendegabriel · Accepted Answer · 2020-10-08 15:58:20Z

2

I was having the same problem. Following the idea of the last post:

one_hot = tf.dtypes.cast(parts[-2] == class_names, dtype = tf.int16)

answered Oct 8, 2020 at 15:58

rezendegabriel

211 bronze badge

Sign up to request clarification or add additional context in comments.

Comments

subbu · Accepted Answer · 2022-01-05 12:34:23Z

1

I think in this line img = tf.io.read_file(file_path) , img is image name instead of actual image. To resolve this problem you can refer to here

It worked for me. Let me know!

answered Jan 5, 2022 at 12:34

subbu

1471 gold badge1 silver badge10 bronze badges

Comments

aldente · Accepted Answer · 2020-09-29 11:13:13Z

0

My guess would be that tf.argmax requires one of these data-types (I can't test this right now)

float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, uint16, complex128, float16, uint32, uint64

so all you need to do is convert the output of

one_hot = parts[-2] == class_names

to int, the "==" evaluates to True/False which is probably not allowed.

edited Sep 29, 2020 at 11:13

answered Sep 29, 2020 at 11:04

aldente

1358 bronze badges

Collectives™ on Stack Overflow

TypeError: Value passed to parameter 'input' has DataType bool not in list of allowed values: float32, float64, int32, uint8, int16, int8

3 Answers 3

Comments

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

3 Answers 3

Comments

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related