-
I want to test, but could not find where to download the models in project?
-
@weiliu89
Thanks for help.I have run the ssd_pascal_video on Nvidia TX2 about 8~9fps. I see the script that it takes video input through VideoDataLayer, and construct the test.prototext, and finally…
-
As mentioned in https://github.com/ApolloResearch/rib/pull/316#issuecomment-1919287670:
> Caching downloaded data (and models?) in some folder on the ssd drive. Best case we can set transformers to o…
-
It seems ONNX format is supported for faster rcnn, yolo and ssd. Is it possible to export these models to TorchScript format.
-
"model_path": 'model_data/mobilenet_ssd_weights.h5'
net['predictions'] = concatenate([net['mbox_loc'],
net['mbox_conf'],
net['mbox…
-
@dusty-nv Every time I run detectnet it takes forever to start running because I think ssd-mobilenetv2 is trying to load. Even though I have ran the script many times it still takes forever to load. I…
-
Command: `detectnet ./combine.avi`
The output:
Source video:
. I converted the model to .dlc, and tried to run using snpe-net-run command... The command runs …
-
Hi @weiliu89
I have just tested SSD with pre-trained reduced VGG network model on Jetson TX1 platform. The fps got only 5-6, same as Jetson TK1 performance. Do you have any idea?
Thanks,
-
Hi weiliu,
I have reported the question about cannot find val2_name_size.txt when running ssd_detect.bin. And with your answer I found the val2_name_size.txt is setted up requirement by deploy.protot…