You shouldn't evaluate the performance of a deep learning model solely on accuracy.
You're missing the whole picture if that's all you're looking at.
There are 3 other factors you should consider when evaluating the performance of your model 👇🏽
#deeplearning #ai
You're missing the whole picture if that's all you're looking at.
There are 3 other factors you should consider when evaluating the performance of your model 👇🏽
#deeplearning #ai
Flops (floating point operations)
This measures of the amount of computation required to train and run a model.
More complex models often require more flops, which can make them more expensive to use.
This measures of the amount of computation required to train and run a model.
More complex models often require more flops, which can make them more expensive to use.
Parameters
The number of parameters in a model can also impact its performance.
Models with more parameters may fit the training data better, but they may also be more prone to overfitting and may not generalize well to new data.
The number of parameters in a model can also impact its performance.
Models with more parameters may fit the training data better, but they may also be more prone to overfitting and may not generalize well to new data.
Latency
This is the time it takes to make a prediction, can be important in certain applications where real-time performance is required.
Ignoring latency when comparing models could lead to misleading conclusions about their performance.
This is the time it takes to make a prediction, can be important in certain applications where real-time performance is required.
Ignoring latency when comparing models could lead to misleading conclusions about their performance.
When comparing the performance of different deep learning models, be sure to take into account flops, params, and latency in addition to accuracy.
This will give you a more complete picture of the trade-offs between different models.
This will give you a more complete picture of the trade-offs between different models.
What else would you add to this?
1. Follow me @DataScienceHarp for more of these
2. RT the tweet below & share w/ your friends
3. Also follow: @nevrekaraishwa2 @SanthoshKumarS_ @GiftOjeabulu_ @Sumanth_077 @Saboo_Shubham_ @_jaydeepkarale @Pauline_Cx
1. Follow me @DataScienceHarp for more of these
2. RT the tweet below & share w/ your friends
3. Also follow: @nevrekaraishwa2 @SanthoshKumarS_ @GiftOjeabulu_ @Sumanth_077 @Saboo_Shubham_ @_jaydeepkarale @Pauline_Cx
https://twitter.com/1248982662481612801/status/1610517689063116801
• • •
Missing some Tweet in this thread? You can try to
force a refresh
