Closed KleinXin closed 5 years ago
Hi, did you use tutorial without any changes?
Yes, I think so.
Can you get the model and script I shared with you?
On 5/7/2019 13:26,Pavel Yakubovskiynotifications@github.com wrote:
Hi, did you use tutorial without any changes?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.
Yeah, I can. Did you try colab tutorial? No any ideas whats wrong.
I got the same problem with other dataset using se_resnext50_32x4d encoder too.
Line 321 bug, change model.predict
-> best_model.predict
@qubvel problem solved, thank you very much
I used se_resnext50_32x4d encoder and Unet decoder to train the segmentation model by following the CamVid tutorial on the webpage
However, the pr_mask is not correct although the accuracy on CamVid test set is very high(iou - 0.7417)
valid: 100%|████████████████████████████████████████████| 233/233 [00:10<00:00, 21.86it/s, bce_dice_loss - 0.3587, iou - 0.7417, f-score - 0.8195]
The trained model and codes can be found here
https://drive.google.com/drive/folders/0B6X3_r_lRbVUODRiM2RhMWMtNDk4NC00NmM1LWEyODEtMTdjNDI5MWJiMmQ4