KerasToTensorRT icon indicating copy to clipboard operation
KerasToTensorRT copied to clipboard

This is a simple demonstration for running Keras model model on Tensorflow with TensorRT integration(TFTRT) or on TensorRT directly without invoking "freeze_graph.py".

Results 6 KerasToTensorRT issues
Sort by recently updated
recently updated
newest added

I got this error. 2018-10-19 17:53:13.158279: W tensorflow/core/common_runtime/bfc_allocator.cc:275] *_______________________****************************************************************____________ 2018-10-19 17:53:13.158377: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at conv_ops.cc:693 : Resource exhausted: OOM when allocating tensor with shape[10000,64,24,24] and type float on...

Thanks for your transform code. then, i'd like to use engine without h5 file how can i save engine?

Hi Jeng, Thanks for your code firstly, I am trying to use your trt_example.py code to optimize my own h5 model. I change frozen_graph = FrozenGraph(model, (img_h, img_w, 1)) to...

The engine creation does not work in Tensor RT 5 due to different commands. Some of the errors: `Using TensorFlow backend. Traceback (most recent call last): File "trt_exampleOG.py", line 9,...

Hi, Thanks for the great example code! I'm trying to compare speed between native, FP32 and INT8 with tftrt_resnet_example.py. Prediction time for resnet50 with gtx 1080ti I find for same...

Thanks for your demo, when I run the raw code, it looks work greatly, in order to verify the effect of tensorrt more precise, I add "warm-up" code before infer...