![]() ![]() ![]() There are multiple books and web resources I have skimmed through. Most of my practice was by coding dozens of models and quick testing them on GPU. It took about 5-6 weeks of practicing for me, mostly on weekends. This is probably because the Colab GPUs have higher user load. I like VSCode's inline code cells which do not clutter code with outputs.Īlso, I thought K80 is an ancient GPU, but surprisingly, I found it giving better perfornace than the modern T4 which powers Google Colab. The reason for using a cloud GPU was, I wanted to use VS Code on SSH, without being limited to Jupyter notebooks in the web browser. So, instead of using Colab or Kaggle, I have used an azure cloud VM with K80 for the exam and for practice as well (it's only about $0.5/hour). A good strategy is to submit basic models for all questions as soon as possible and then start improving them as the time allows. Some questions require tweaking of the code for hours to get that required accuracy on test data. The areas covered are Computer vision, NLP and Time-series forecasting. My models have scored 5/5 in all categories. There are five categories, with one model to develop in each category. I have used VS Code anyway for codng and then submitted using pycharm. The exam is very insistent on using latest versions of tensorflow, python and pycharm. It appears that there are less than 2400 people who got certified since the launch of the exam in early 2020. The exam handbook is here and exam web page here. Requires you to use a specific IDE and a special exam plugin.Grading is based on the model accuracy against test data.No multiple-choice type questions (coding only).Long duration of exam: 5 hours, but that's barely enough.Thought of adding a few notes here, because it appeared to me as a bit unconventional exam. I took this exam recently ( my credential). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |