{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/e58a843073014228b3f54890796d5347\" frameborder=\"0\" width=\"1766\" height=\"1324\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1324,"width":1766,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1324,"thumbnail_width":1766,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/e58a843073014228b3f54890796d5347-7e1e0c8cbf16e787.gif","duration":358.419,"title":"Flower Image Recognition with Deep Learning 🌸","description":"In this video, I demonstrate my flower image recognition model based on CNN and transfer learning using EfficientNet B0. The model predicts 13 flower species with an impressive accuracy of 94.32% and an F1 score of 0.9434. I showcase live predictions and file selections, achieving high confidence levels, such as 99.6% for marigold. Additionally, I discuss the model's ability to store scan history and visualize accuracy. I encourage viewers to explore the predictions and provide feedback."}