-
2017-09-25 00:09:25.111761: I tensorflow/core/common_runtime/gpu/gpu_device.cc:908] DMA: 0
2017-09-25 00:09:25.111772: I tensorflow/core/common_runtime/gpu/gpu_device.cc:918] 0: Y
2017-09-25 00:…
-
@chuanqi305 ,Hi, i use my own data to train the mobilenet ssd model ,everything is fine,the model size is 22.2MB, but something is wrong when i run the demo ,the GPU memory is 700M, and the spend tim…
-
While compiling ssd_mobilenet_v1_coco_2018_01_28 onnx model, got the following error:
"Failed to load operator Loop"
->auto::operator()(int)->auto: block: [1320,0,0], thread: [102,0,0] Assertion `index >= -size…
-
I am currently trying to apply the PersonDetection module and use my own custom dataset for object detection.
I'm trying to train a transition with the mobilenet ssd 2017_11_17 model, but I can't t…
-
## 🐛 Bug
> RuntimeError: CUDA out of memory. Tried to allocate 90.73 GiB (GPU 0; 1.96 GiB total capacity; 12.11 MiB already allocated; 1.13 GiB free; 1.89 MiB cached)
## To Reproduce
Steps to…
-
Hi, luffic,
I used your SSD model to train and output a weight file (.pth) on win7. And I want to inference in C++. But I got a problem when I converting. My converting code as follows:
-
### System information
- **What is the top-level directory of the model you are using**: object_detection
- **Have I written custom code (as opposed to using a stock example script provided in Tenso…
-
Hi, I'm doing model translation ,when I importing the SSD caffemodel and prototxt, it comes this problem, and when I delete the norm_param , it comes "no field named prior_box_param", I don't know wha…