IndexError

[justinkkgoh]

I am trying to run eval.py on my own dataset and initially ran into a size mismatch error as described here #36. However I am now getting this IndexError. Am wondering if anybody else encountered a similar issue?

`Loading model...Ignoring "Error(s) in loading state_dict for Yolact: size mismatch for prediction_layers.0.conf_layer.weight: copying a param with shape torch.Size([33, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([243, 256, 3, 3]). size mismatch for prediction_layers.0.conf_layer.bias: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model is torch.Size([243]). size mismatch for semantic_seg_conv.weight: copying a param with shape torch.Size([10, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 256, 1, 1]). size mismatch for semantic_seg_conv.bias: copying a param with shape torch.Size([10]) from checkpoint, the shape in current model is torch.Size([80])." Done.

Traceback (most recent call last): File "/content/yolact/eval.py", line 1105, in evaluate(net, dataset) File "/content/yolact/eval.py", line 956, in evaluate prep_metrics(ap_data, preds, img, gt, gt_masks, h, w, num_crowd, dataset.ids[image_idx], detections) File "/content/yolact/eval.py", line 468, in prep_metrics ap_obj = ap_data[iou_type][iouIdx][_class] IndexError: list index out of range`

[KennyChen880127]

Do your custom config 'dataset''s name == 'num_classes': len('dataset''s name.class_names)+1?