ARTIST HAWKINS

3y

OutKast, Jermaine Dupri, Gucci, RHQ, and more. :)

You're right, but nooo.

frenchpress

3y

tf.saved_model.save(model, "path")
The get requests result says the model is deployed:

{ "version": "4", "state": "AVAILABLE", "status": { "error_code": "OK", "error_message": "" } }
I am converting my image to base64 using the 'react-native-image-base64' library and sending it using a post request with the correct format. However, as the error code says it expects a float

"error": "Failed to process element: 0 of \'instances\' list. Error: Invalid argument: JSON Value: {"Base64 image string here"} Type: Object is not of expected type: float"
with the following request :

curl --request POST \
--url http://192.165.1.79:8001/v1/models/saved_model:predict \
--header 'content-type: application/json' \
--data '
{
"instances":

{
"b64": "HBwcIiIiIiIiHh4eGhoaGBgYExMTEBAQERERERERDw8PCQkJBQ.."
}

}'
current signature def

signature_def'serving_default':
The given SavedModel SignatureDef contains the following input(s):
inputs'conv2d_input' tensor_info:
dtype: DT_FLOAT
shape: (-1, 102, 136, 3)
name: serving_default_conv2d_input:0
The given SavedModel SignatureDef contains the following output(s):
outputs'dense' tensor_info:
dtype: DT_FLOAT
shape: (-1, 2)
name: StatefulPartitionedCall:0
Method name is: tensorflow/serving/predict

frenchpress

3y

tf.saved_model.save(model, "path")
The get requests result says the model is deployed:

{ "version": "4", "state": "AVAILABLE", "status": { "error_code": "OK", "error_message": "" } }
I am converting my image to base64 using the 'react-native-image-base64' library and sending it using a post request with the correct format. However, as the error code says it expects a float

"error": "Failed to process element: 0 of \'instances\' list. Error: Invalid argument: JSON Value: {"Base64 image string here"} Type: Object is not of expected type: float"
with the following request :

curl --request POST \
--url http://192.165.1.79:8001/v1/models/saved_model:predict \
--header 'content-type: application/json' \
--data '
{
"instances":

{
"b64": "HBwcIiIiIiIiHh4eGhoaGBgYExMTEBAQERERERERDw8PCQkJBQ.."
}

}'
current signature def

signature_def'serving_default':
The given SavedModel SignatureDef contains the following input(s):
inputs'conv2d_input' tensor_info:
dtype: DT_FLOAT
shape: (-1, 102, 136, 3)
name: serving_default_conv2d_input:0
The given SavedModel SignatureDef contains the following output(s):
outputs'dense' tensor_info:
dtype: DT_FLOAT
shape: (-1, 2)
name: StatefulPartitionedCall:0
Method name is: tensorflow/serving/predict

Totally Spice

3y

LAST NIGHT A DJ SAVED MY LIFE!

THEREALHNDRXXFREE

3y

Man i would love to quote that old avy rn

ARTIST HAWKINS

3y

That's New Yooork.

frenchpress

3y

quick

THEREALHNDRXXFREE

3y

Man i would love to quote that old avy rn

EchiBridgers

3y

@KodakSpice

frenchpress

3y

i also have people's old avis saved in tabs on my phone

Totally Spice

3y

u kno this one?

frenchpress

3y

she's hot

im almost there

3y

post mines

Totally Spice

3y

Of Course

frenchpress

3y

true. couldn't get very far otherwise.

ARTIST HAWKINS

3y

Underrated.

Jada's one of my faves.

Totally Spice

3y

ed sheeran

frenchpress

3y

it's different. also he sucks