Category AI

47. SSD_Inception_V2 vs SSD_MobileNet_V2

COMPARING MODELSLast week, I was able to deploy SSD_mobileNet_v2, so for comparison, this time I deployed SSD_Inception_V2. PREREQUISITE– DeepStream 5.0.1– Jetpack 4.4– Tensorflow 1.15.0 ( If you haven’t installed it yet, check out my last post) REFERENCES– https://havedatawilltrain.com/stream-of-the-jest/– IMPLEMENTATION1.…

43. Generating Faces with GAN Part 2

PART 2I’ve tried generating faces to see how many images and epochs you need to get something recognizable. For part 1, I’ve done 23 epochs with about 20,000 images, and found that the machine was able to create something recognizable…

41. Generating Faces with GAN

How Much Is Enough? The last time I used gan(Generating cityscapes), the output was not recognizable due to a lack of data. So, as for my next step I wanted to find out how much data and epochs you need…

38. Data Preparation

PREPARING DATAWhen starting an AI project, 80% of the work is on cleaning data for the model. In most cases, the data are not clean and the data source is not centrally managed. That’s when a data management platform comes…

37. Hyperparameter Tuning for ML Models

TUNINGI’ve learned that the predictions machine-learning models make, vary widely depending on the hyperparameters. However, manually testing these hyperparameters can be quite inefficient. In order to resolve that, I found a software framework to automate this process called Optuna, so…

36. Generating a Non-Existent Cityscape

GENERATIVE ADVERSARIAL NETWORKThere is a class of machine learning framework called GAN which generates new data from data. One of the most popular use cases for GAN is generating people’s faces who don’t exist. As I was learning more about…

33.OCR-ing Japanese

■PRECISION OF OCR API One of the most often projects my company is helping are related to Natural Language Processing. This is because for most companies, digital transformation is becoming their highest priority and NLP is almost inevitable when it…