-
loss_bbox is not converge.other loss(loss_cls,loss_rpn_cls,loss_bbox) is converge.can I push the code to you for debug.
-
Hi,
I met the issue during ResNet-50 training:
psroi_pooling_layer.cu:108] Check failed: error == cudaSuccess (9 vs. 0) invalid configuration argument
Ubuntu 14.04 + one 1080 GPU card.
Any …
-
I try to use do_python_eval() in lib/dataset/imagenet_vid.py to calculate mAP by classes.
But I get a results like :
> AP for airplane = 0.0047
> AP for antelope = 0.0028
> AP for bear = 0.0019…
-
1. The script_rfcn_demo.m is work well with Resnet101
2. But the matlab go crash when running with Resnet50/101, the code is down at line 117 "caffe_solver.step(1)" of rfcn_train.m, without an…
-
# Reference
- [ ] [Tensorflow detection model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md)
- [ ] [Quick Start: Training a pet detecto…
-
Try to train on Resnet50 FasterRCNN on VOC, got nan loss in the begin of training process:
```
I0812 13:02:23.224562 15010 caffe.cpp:248] Starting Optimization
I0812 13:02:23.224596 15010 solver.…
-
After training finished, I ran this command:
python tools/test_net.py --dataset my_dataset --cfg configs/baselines/e2e_faster_rcnn_R-50-C4_1x.yaml --load_ckpt Outputs/e2e_faster_rcnn_R-50-C4_1x/Feb…
-
where is xception like network code which is written in original paper?
-
Error during installation. Tested on a x86 and aarch64 (Jetson TX2) machine.
```
nvidia@jetson-dev:~/code/tf_trt_models (master)$ ./install.sh python3
python3
Downloading protoc
~/code/tf_trt_m…
-
在ubuntu 配置了R-FCN的python 接口，也简单训练rfcn_end2end_ohem.sh（ResNet101），在voc数据集上精度跟github上大致相同，但是在将基础网络修改为resnext50-32x4d时，参考\det\faster_rcnn\models\pascal_voc\resnext50-32x4d工程下resnext50网络定义文件，并将网盘中resne…
hp-93 updated
6 years ago