درخت حوزه‌های تخصصی

The Moroccan education system has undergone several reforms in recent years, thus concluded by the strategic vision, especially project 9 which has valued the continuing training of educational actors and framework law 51-17 in articles 34 and 35 which valued the continuous development of skills of teachers in Morocco, In this perspective the Ministry of National Education has reserved significant budgets to operationalize the continuing training of teachers on the one hand and it is committed to a Moroccan-American partnership within the framework of the Millennium project Challenge Account-Morocco. By committing to the establishment-challenge project, the ministry has set up a set of priorities, in particular the operationalization of the digital strategy for schools declared by decree 2.20.474, thus benefiting from the contribution of digital and while trying to overcome some constraints related to face-to-face training, a new regime that is continuous online training is implemented, it is the e-takwine platform. In addition, given the interest that evaluation represents for maintaining and improving the quality of a digital training device, we opted in this research, by evaluating the technopedagogical modality of e-takwine reserved at the start of the continuing training of novice teachers in Morocco and then developed for the training of all second cycle teachers from the start of the 2021-2022 school year. The sampling of our research is represented by 362 professors from the region of Fés –Meknes belonging to two different teaching cycles, and who followed their training for three months in six training modules in a more or less assiduous manner, Similarly, to conduct our survey, we administered two online questionnaires to participating teachers, in order to judge the functionality and ergonomics of the platform being researched. Finally, confirming to us that despite the satisfaction of the majority of participants with respect to the functional quality and the contribution of the device, some difficulties were noted at the levels: technical (compatibility, accessibility), functional or even with regard to technological knowledge.

The aim of this study is to evaluate the performance of the pre-trained models and compare them with the probability percentage of prediction in terms of execution time. This study uses the COCO dataset to evaluate both pre-trained image recognition and object detection, models. The results revealed that Tiny-YoloV3 is considered the best method for real-time applications as it takes less time. Whereas ResNet 50 is required for those applications which require a high probability percentage of prediction, such as medical image classification. In general, the rate of probability varies from 75% to 90% for the large objects in ResNet 50. Whereas in Tiny-YoloV3, the rate varies from 35% to 80% for large objects, besides it extracts more objects, so the rise of execution time is sensible. Whereas small size and high percentage probability makes SqueezeNet suitable for portable applications, while reusing features makes DenseNet suitable for applications for object identification.