TimoSaemann / ENet

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
577 stars 276 forks source link

Bad test #72

Open Dawson-huang opened 5 years ago

Dawson-huang commented 5 years ago

when I run: python test_segmentation.py --model ENet/prototxts/enet_deploy_final.prototxt \ --weights ENet/enet_weights_zoo/cityscapes_weights.caffemodel \ --colours ENet/scripts/cityscapes19.png \ --input_image ENet/example_image/munich_000000_000019_leftImg8bit.png \ --out_dir ENet/example_image/ the result image is nice as your show! But when I change the test image like this: 0 I get a bad result like this: 0_enet and others too: 100 So, like the topic that the model is a little bad to test, do you know the reason and guide me? Thanks.