Kediska CNN-ku-salaysan ee Gobolka

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay fikradda asaasiga ah ee CNN-ku-salaysan gobolka?
   • Soo jeedi gobollada musharaxiinta, ka dibna kala saar oo ku dheji walxaha mid kasta
   • U samee hal calaamad sawirka oo dhan
   • Cadaadi sawirka ka hor inta aanad farsamayn
   • Marka hore u beddel sawirka miisaan cawl
2. Why was the original R-CNN computationally expensive?
   • It trained without image pixels
   • It ran a CNN separately on each proposed region
   • It required one human label per test image
   • It computed only one shared feature map
3. Muxuu Soo Bandhigay Degdegga R-CNN si uu u beddelo Raadinta Xulashada?
   • CNN laf dhabar ka weyn
   • Tallaabo beddelasho miisaan cawl leh
   • Shabakadda Soo jeedinta Gobolka (RPN)
   • Shabakad neerfaha ah oo soo noqnoqda
4. Maxay RoI kasbataa?
   • Waxay tirtirtaa gobollada dhibcaha hooseeya
   • Waxay kordhisaa xallinta sawirka
   • Waxay isku daraysaa dhammaan gobollada hal
   • Wuxu beeraa oo ka beddelaa sifooyinka khariidad sifada la wadaago ee gobol kasta
5. Waa maxay awoodda dheeraadka ah ee Mask R-CNN ku daro?
   • Maaskaro qaybinta heerka Pixel ee shay kasta oo la ogaado
   • Qoraal maqal ah
   • Turjumaada qoraalka
   • Moolka 3D ee hal pixel
6. What training objective does Mask R-CNN use for its classification, box, and mask branches?
   • Only a pixelwise mask loss with no classification
   • A multi-task loss that combines classification, bounding-box regression, and mask losses
   • A language-model next-token loss
   • A region-proposal loss with no object classification
7. What alignment problem does RoIAlign address compared with RoI pooling?
   • It replaces the Region Proposal Network with Selective Search
   • It removes all need for a shared feature map
   • It avoids the coordinate quantization that can misalign extracted region features
   • It predicts a class label before processing the image
8. How should two-stage and single-stage detector speed/accuracy be compared?
   • Two-stage models are always more accurate and faster
   • Single-stage models cannot detect multiple objects
   • The architectures have identical pipelines
   • Using a specified benchmark and implementation, because the tradeoff is not universal