Hi
Im trying to run tensorrt ssd sample on windows 10.
it needs “ssd.proto” and “VGG_VOC0712_SSD_300x300_iter_120000.caffemodel”
i downloaded .caffemodel from the link in readme, but cant find .proto
in the doc, its says
“The network is defined in a prototxt file which is shipped with the sample and located in the data/ssd directory.”
but there are only ssd_coco_labels.txt and 2 .ppm files inside (\TensorRT-5.0.2.6\data\ssd)
where can i find it?
Edit:
thanks, i run the sample successfully.
file is attached in case someone need it. ssd_proto.zip (4.2 KB)
C++ Samples
sampleSSD
This sample demonstrates how to perform inference on the Caffe SSD network in TensorRT, use TensorRT plugins to speed up inference, and perform INT8 calibration on an SSD network. To generate the required prototxt file for this sample, perform the following steps:
Download models_VGGNet_VOC0712_SSD_300x300.tar.gz from: models_VGGNet_VOC0712_SSD_300x300.tar.gz - Google Drive
Extract the contents of the tar file;
tar xvf
~/Downloads/models_VGGNet_VOC0712_SSD_300x300.tar.gz
Edit the deploy.prototxt file and change all the Flatten layers to Reshape operations with the following parameters:
reshape_param {
shape {
dim: 0
dim: -1
dim: 1
dim: 1
}
Update the detection_out layer by adding the keep_count output, for example, add:
top: “keep_count”
Rename the deploy.prototxt file to ssd.prototxt and run the sample.
To run the sample in INT8 mode, install Pillow first by issuing the $ pip install Pillow command, then follow the instructions from the README.
Following the TensorRT-Release-Notes and changed related layers,but I got a err msg “could not parse layer type Reshape”
Win10+CUDA9.0+CUDNN7.3+TensorRT-5.0.4.3