how can I test a pre trained model on my custom images ?

[kartikwar]

No description provided.

[kartikwar]

Also tried to run on coco dataset

Got a result like this

{
"image_id":139,
"category_id":62,
"bbox":[
292.0556945800781,
216.36961364746094,
61.314727783203125,
103.17518615722656
],
"score":0.9969334602355957,
"segmentation":{
"size":[
426,
640
],
"counts":"TUj3l0h;e0C=@a0NO3:F6JM3M3M3O1N1UOZEQOi:n0k0N1O1O10000001O0010O010O3M5K4L1018Ga0_O=B0NG;G9ZOk0K0N3N101N101O0000001O00SD@P;?nDMi:3UE1i:OWEAJLP;c0RE]Od;e0XD\Oj;R100001EnCYOW<`0g0@iTg3"
}

I dont see any segmentation masks in this, not sure how to make sense of the segmentation object that I am getting here

[wondervictor]

Hi @kartikwar you can use thedemo.py to infer your own images. BTW, you can refer to this issue #9