-
The version of mxnet is v0.10.0
I managed to run the demo, but when I try to train, an error occurs:
```
Namespace(cfg='experiments/fgfa_rfcn/cfgs/resnet_v1_101_flownet_imagenet_vid_rfcn_end2end_…
-
Found Detectron ops lib: /usr/local/lib/libcaffe2_detectron_ops_gpu.so
E1031 22:55:04.712018 19990 init_intrinsics_check.cc:43] CPU feature avx is present on your machine, but the Caffe2 binary is no…
-
@Orpine
F1013 12:05:22.696523 14673 net.cpp:784] Cannot copy param 0 weights from layer 'rpn_conv/3x3'; shape mismatch. Source param shape is 512 1024 3 3 (4718592); target param shape is 512 2048 3…
-
I try to train a model on my own custom dataset,.
I first converted my dataset to coco format and densepose format .
Then I added my dataset path into dataset_catalog.py and created the correct link…
-
I want to train the FPN_R-FCN including "hole algorithm" with R-FCN module in Detectron. Before that, I have successfully trained the FPN_R-FCN without "hole algorithm". But when I modified some codes…
-
-
Hello, is there anything wrong with your provided rfcn model?
When i run 'demo_rfcn.py', following message appears
![image](https://cloud.githubusercontent.com/assets/10908786/24287126/432d0b32-10b3…
-
Hi, thanks for the great work!
Ran to an out of memory issue when we were running test_net.py on COCO dataset with 2 TITAN X set up. Installations were fine and coco datasets were included in /lib…
ghost updated
5 years ago
-
Seems like the latest checkpoint file is not compatible with the latest repository commit + Tensorflow version? The model trains just fine but clearly the checkpoint has a naming mismatch with what is…
-
- OpenCV => 3.4.1
- Operating System / Platform => Windows 64 Bit
- Compiler => Visual Studio 2015
Detailed description
I trained a new RFCN model (ResNet-50 with pascal format data sets) usin…