Tensorflow #7470
Merged
Tensorflow #7470
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ev-mp
reviewed
Oct 4, 2020
wrappers/tensorflow/README.md
Outdated
| feed_dict={image_tensor: image_expanded}) | ||
| ``` | ||
|
|
||
| Finally we will assign random persistent color to each detection class and draw a bounding box around the object. We filter out low confidence predictions using `score` output. |
wrappers/tensorflow/README.md
Outdated
| verts = np.asanyarray(points.get_vertices()).view(np.float32).reshape(-1, W, 3) # xyz | ||
| ``` | ||
|
|
||
| This allows us to query XYZ coordinates of each detected object and to seperate individual coordinates (in meters): |
wrappers/tensorflow/README.md
Outdated
|
|
||
| ## Part 3 - Deploying TensorFlow model using OpenCV | ||
|
|
||
| While TensorFlow is convinient to install and use, it is not as convinient as OpenCV. OpenCV is ported to most platforms and is well optimised for various types of CPUs. It also comes with built-in DNN module capable of loading and using TensorFlow models without having TensorFlow (or its dependencies) installed. |
wrappers/tensorflow/README.md
Outdated
| Unet offers significant advantages compared to classic autoencoder architecture, improving edge fidelity (see image below). | ||
|
|
||
|  | ||
| ###### The image is taken from the article reffered above. |
wrappers/tensorflow/README.md
Outdated
| very good at detecting more and more features, the first few layers of a convolution network capture a very small semantic information and lower level | ||
| features, as you go down these features become larger and larger, but when we throw away information the CNN | ||
| knows only approximate location about where those features are. | ||
| When we upsample we get the lost information back (by the concatination process) |
wrappers/tensorflow/README.md
Outdated
| #### Data Augmentation | ||
| To help the neural network learning image features we decide to crop input images into tiles of 128x128 pixels. | ||
|
|
||
| Each ground truth image has a corressponding depth and infrared image. Given that, the dataset is augmented as following: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adding Tensorflow wrapper.
Track on: DSO-15262