diff options
author | Asim Shankar <ashankar@google.com> | 2016-12-06 16:59:55 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2016-12-06 17:05:37 -0800 |
commit | bd65cda4051a042003096096ab9b05c73a15e65c (patch) | |
tree | 20d5be971859994ad11d4860c658e6b24932a8be /tensorflow/examples/label_image | |
parent | d95969fe12764a2a5993a8a4b9e76d72aa3be818 (diff) |
Java: LabelImage using Inception example.
Command-line program to:
- Construct an image normalization graph G1
- Execute G1 in a session to produce a tensor of a batch of images
- Import a pre-trained inception model into a graph G2
- Execute G2 in a session to find the best matching label
In other words, the Java equivalent of:
- C++ example https://github.com/tensorflow/tensorflow/tree/abbb4c1/tensorflow/examples/label_image
- Go example
https://github.com/tensorflow/tensorflow/blob/c427b7e89d1498b78d361bfe7345b2636a438893/tensorflow/go/example_inception_inference_test.go
Another step in the journey that is #5
Change: 141247499
Diffstat (limited to 'tensorflow/examples/label_image')
-rw-r--r-- | tensorflow/examples/label_image/README.md | 12 |
1 files changed, 8 insertions, 4 deletions
diff --git a/tensorflow/examples/label_image/README.md b/tensorflow/examples/label_image/README.md index e427ff7845..62385312b6 100644 --- a/tensorflow/examples/label_image/README.md +++ b/tensorflow/examples/label_image/README.md @@ -1,7 +1,10 @@ # TensorFlow C++ Image Recognition Demo This example shows how you can load a pre-trained TensorFlow network and use it -to recognize objects in images. +to recognize objects in images in C++. For Java see the [Java +README](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/java), +and for Go see the [godoc +example](https://godoc.org/github.com/tensorflow/tensorflow/tensorflow/go#ex-package). ## Description @@ -10,9 +13,9 @@ in on the command line. ## To build/install/run -The TensorFlow `GraphDef` that contains the model definition and weights -is not packaged in the repo because of its size. Instead, you must -first download the file to the `data` directory in the source tree: +The TensorFlow `GraphDef` that contains the model definition and weights is not +packaged in the repo because of its size. Instead, you must first download the +file to the `data` directory in the source tree: ```bash $ wget https://storage.googleapis.com/download.tensorflow.org/models/inception_dec_2015.zip -O tensorflow/examples/label_image/data/inception_dec_2015.zip @@ -49,6 +52,7 @@ I tensorflow/examples/label_image/main.cc:207] academic gown (896): 0.0232407 I tensorflow/examples/label_image/main.cc:207] bow tie (817): 0.0157355 I tensorflow/examples/label_image/main.cc:207] bolo tie (940): 0.0145023 ``` + In this case, we're using the default image of Admiral Grace Hopper, and you can see the network correctly spots she's wearing a military uniform, with a high score of 0.6. |