Skip to content

Instantly share code, notes, and snippets.

@dipanjanS
Created September 20, 2019 10:36
Show Gist options
  • Save dipanjanS/831aa430f15b20db54d0d7d9cfe7598b to your computer and use it in GitHub Desktop.
Save dipanjanS/831aa430f15b20db54d0d7d9cfe7598b to your computer and use it in GitHub Desktop.
%%time
sample_test_data = test_images
sample_test_labels = test_labels
IMG_DIMS = (32, 32)
sample_test_data_processed = (np.array([resize_image_array(img,
img_size_dims=IMG_DIMS)
for img in np.stack([sample_test_data]*3,
axis=-1)])) / 255.
data = json.dumps({"signature_name": "serving_default",
"instances": sample_test_data_processed.tolist()})
HEADERS = {'content-type': 'application/json'}
MODEL2_API_URL = 'http://localhost:8501/v1/models/fashion_model_serving/versions/2:predict'
json_response = requests.post(MODEL2_API_URL, data=data, headers=HEADERS)
predictions = json.loads(json_response.text)['predictions']
predictions = np.argmax(np.array(predictions), axis=1)
prediction_labels = [class_names[p] for p in predictions]
len(prediction_labels)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment