How to use the tfserver.process_classification_prediction function in tfserver
To help you get started, we’ve selected a few tfserver examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
visipedia / tf_classification / tfserving / client.py View on Github 
image_data = []
for fp in args.image_paths:
with open(fp) as f:
data = f.read()
image_data.append(data)
# Get the predictions
t = time.time()
predictions = tfserver.predict(image_data, model_name=args.model_name,
host=args.host, port=args.port, timeout=args.timeout
)
dt = time.time() - t
print("Prediction call took %0.4f seconds" % (dt,))
# Process the results
results = tfserver.process_classification_prediction(predictions, max_classes=args.num_results)
# Print the results
for i, fp in enumerate(args.image_paths):
print("Results for image: %s" % (fp,))
for name, score in results[i]:
print("%s: %0.3f" % (name, score))
print()
