-
i want to use the fasterRCNN_FPN to do detection. But the num_class of pretrained model on coco dataset is 81, mine dataset just has one class, And it throw an exception.
File "/home/ed/anaconda…
-
Updated from recent code changes in tensorpack/FasterRCNN. A previously working training (on own dataset) is now giving following error:
jwnsu updated
5 years ago
-
用你训练好的的DOTA模型测试效果为什么是这样子？ 是需要修改哪里的cfg文件吗？
-
Pulled latest tensorpack today and run fasterRCNN training, got following error (after successful data loading and graph building on 8 GPUs):
```
Traceback (most recent call last):/lib/python3.5/sit…
jwnsu updated
5 years ago
-
I report two errors in the official [train faster-rcnn on voc tutorial](https://gluon-cv.mxnet.io/build/examples_detection/train_faster_rcnn_voc.html#sphx-glr-build-examples-detection-train-faster-rc…
-
## Issue description
RuntimeError: [enforce fail at generate_proposals_op.cc:247] im_info_tensor.dims() == (vector{num_images, 3}). 0 vs 1 3Error from operator:
Provide a short description.
I am…
-
Hello,
I would like to do **model-agnostic meta learning** in tensorpack
The training algorithm of a **classification** task using model-agnostic meta learning is below:
We have fθ as the model…