Practice Test 1 | Google Cloud Certified Professional Data Engineer | Dumps | Mock Test
You want to build a machine learning model to recognize images for Thai cuisine restaurants. You are provided with several image samples for each dish and its name. You used AutoML Vision to build the model. You split the samples into training and test sets. You uploaded the training set to Google Cloud with labels and build the model on AutoML vision. When you tested the newly built model with the test, the confusion matrix shows high false positives with the model confused between different labels. How can you fix the model’s accuracy? (Select TWO)
A. Remove all images with bad quality.
B. Sort images by how “confused” the model is and check if they are labeled correctly.
C. If you have a very low training set, consider removing labels altogether.
D. Let AutoML Vision decide which images to be considered for training or testing.
Correct Answers – B and C
Description:
Google Cloud provies a machine learning service called AutoML to quickly build models for you. AutoML Vision is one of its products which you can start with a training set as little as a dozen photo samples and AutoML takes care of the rest.
While iterating on your model, if the model’s quality levels are not up to expectations, you can go back to earlier steps to improve the quality:
- AutoML Vision allows you to sort the images by how “confused” the model is, by the true label and its predicted label. Look through these images and make sure they’re labeled correctly.
- Consider adding more images to any labels with low quality.
- You may need to add different types of images (e.g. wider angle, higher or lower resolution, different points of view).
- Consider removing labels altogether if you don’t have enough training images.
- Remember that machines can’t read your label name; it’s just a random string of letters to them. If you have one label that says “door” and another that says “door_with_knob” the machine has no way of figuring out the nuance other than the images you provide it.
- Augment your data with more examples of true positives and negatives. Especially important examples are the ones that are close to the decision boundary (i.e. likely to produce confusion but still correctly labeled).
- Specify your own TRAIN, TEST, VALIDATION split. The tool randomly assigns images, but near-duplicates may end up in TRAIN and VALIDATION which could lead to overfitting and then poor performance on the TEST set.
Once you’ve made changes, train and evaluate a new model until you reach a high enough quality level.
Source(s):
Cloud AutoML Vision – Evaluating Models:
Comments are closed, but trackbacks and pingbacks are open.