A selection of the best models are available for download from my Google Drive. After downloading simply store the pre-trained model directories in the experiments directory.
A summary of the models and their results is below
TODO Add summary table
Models evaluated on the Pascal VOC, MS-COCO or ImageNet-DET dataset use the image based metrics: Box Area's - Small <32, Medium 32-96, Large >96. While models evaluated on the ImageNet-VID datasets use the video based metrics: Box Area's - Small <50, Medium 50-150, Large >150 - Instance's Speed (motion IoU) - SLow >0.9, MOderate 0.7-0.9, FAst <0.7
These models are trained and tested on their respective datasets. The Pascal VOC and MS-COCO models are taken from the GluonCV Model Zoo
.......
Coming Soon
.......
Coming Soon
.......
Coming Soon
.......
Coming Soon
.......
Coming Soon