Fix dead links

Author: DEKHTIARJonathan

README.md

@@ -16,8 +16,8 @@ performance of TF-TRT. For more information see
 
 ## Examples
 
-* [Image Classification](tftrt/examples/image_classification)
-* [Object Detection](tftrt/examples/object_detection)
+* [Image Classification](tftrt/benchmarking-python/image_classification)
+* [Object Detection](tftrt/benchmarking-python/object_detection)
 
 
 # Using TensorRT in TensorFlow (TF-TRT)
@@ -38,7 +38,7 @@ If you want to use TF-TRT on NVIDIA Jetson platform, you can find
 the download links for the relevant Tensorflow pip packages here:
 https://docs.nvidia.com/deeplearning/dgx/index.html#installing-frameworks-for-jetson
 
-You can also use [NVIDIA's Tensorflow container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tensorflow)(tested and published monthly). 
+You can also use [NVIDIA's Tensorflow container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tensorflow)(tested and published monthly).
 
 ## Installing TensorRT
 

tests/utils.py

@@ -23,7 +23,7 @@ def assertNotRaises(self, exc_type):
             raise self.failureException('{} raised'.format(exc_type.__name__))
 
 
-_excludes_paths = ["tftrt/blog_posts/", "tftrt/examples/third_party"]
+_excludes_paths = ["tftrt/blog_posts/"]
 
 
 def list_all_py_files():

tftrt/benchmarking-cpp/README.md

@@ -1,6 +1,6 @@
 # Benchmark Runner
 
-This straightforward example uses TF's C++ API to serve a saved model and measure throughput. Built off of the [example here](https://github.com/tensorflow/tensorrt/tree/fb0a2cf638c8707041e42451c601247f04c7e6d8/tftrt/examples/cpp/image-classification).
+This straightforward example uses TF's C++ API to serve a saved model and measure throughput. Built off of the [example here](https://github.com/tensorflow/tensorrt/tree/master/tftrt/benchmarking-python/cpp/image-classification).
 
 ## Docker Environment
 

tftrt/benchmarking-python/object_detection/README.md

@@ -10,7 +10,7 @@ validating accuracy (e.g. mAP).
 <a name="setup"></a>
 ## Setup
 
-Install object detection dependencies (from tftrt/examples/object_detection)
+Install object detection dependencies (from tftrt/benchmarking-python/object_detection)
 
 ```bash
 git submodule update --init

tftrt/examples-cpp/mnist_demo/README.md

@@ -24,7 +24,7 @@ cp /opt/tensorflow/nvbuild* /opt/tensorflow/bazel_build.sh .
 
 ### Build the TF-TRT example
 ```
-cd tensorrt/tftrt/examples/cpp/image-classification
+cd tensorrt/tftrt/examples-cpp/mnist_demo
 mkdir build && cd build
 cmake ..
 make
@@ -38,12 +38,12 @@ python mnist_train.py
 ### Run TF-TRT conversion and infer the converted model
 Get input data
 ```
-cd /workspace/tensorrt/tftrt/examples/cpp/image-classification
+cd /workspace/tensorrt/tftrt/examples-cpp/mnist_demo
 wget -O - http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz | gunzip > t10k-images.idx3-ubyte
 
 ```
 Run inference
 ```
-cd /workspace/tensorrt/tftrt/examples/cpp/image-classification/build
+cd /workspace/tensorrt/tftrt/examples-cpp/mnist_demo/build
 TF_CPP_VMODULE=trt_convert=2,trt_optimization_pass=2,trt_engine_utils=2,trt_engine_op=2,segment=2,trt_shape_optimization_profiles=2,trt_lru_cache=2,convert_graph=2,trt_engine_resource_ops=2 ./tf_trt_example --saved_model_dir=/workspace/tensorflow-source/tf_trt_cpp_example/mnist_model --mnist_data=/workspace/tensorflow-source/tf_trt_cpp_example/t10k-images.idx3-ubyte
 ```