Tadayoshi Sato created CAMEL-20895:
--------------------------------------
Summary: camel-djl - The image classification predictors should
not round the resulted probabilities
Key: CAMEL-20895
URL: https://issues.apache.org/jira/browse/CAMEL-20895
Project: Camel
Issue Type: Improvement
Components: camel-ai
Affects Versions: 4.6.0
Reporter: Tadayoshi Sato
Currently, both {{ZooImageClassificationPredictor}} and
{{CustomImageClassificationPredictor}} transform the resulted
{{Classifications}} objects into maps of {{Map<String, Float>}}. However, the
data type of {{Classifications}} is a map from the class name to probability
with {{String -> Double}}, thus the precision is lost in the mapping.
It doesn't seem to be a good transformation in the following points:
- Sometimes rounding from double to float loses not only precision but also
accuracy of the value
- The [Softmax|https://en.wikipedia.org/wiki/Softmax_function] function used in
the classification problems expects the probabilities to sum up to {{1.0}}, but
due to the loss of accuracy above the premise seems to be broken to a large
extent.
- Finally, probably it's just better to simply return the {{Classifications}}
object rather than converting it to a {{Map}} because the class already
provides useful methods such as {{best()}}, {{topK()}}, etc. so that downstream
components can easily extract the conclusions from the output out of the box;
if we just provide it as a map, downstream is required to craft some manual
calculations upon the result every time.
In conclusion, I think it's better for {{ZooImageClassificationPredictor}} and
{{CustomImageClassificationPredictor}} to simply return the output as
{{Classifications}}.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
