Merge pull request #806 from RedisAI/backends_update

changed PT and TF versions

Author: DvirDukhan

.circleci/config.yml

@@ -359,7 +359,7 @@ jobs:
       enabled: true
       docker_layer_caching: true
       resource_class: gpu.nvidia.small
-      image: ubuntu-1604-cuda-11.1:202012-01
+      image: ubuntu-2004-cuda-11.2:202103-01
 
     steps:
       - build-and-test-gpu-steps
@@ -371,7 +371,7 @@ jobs:
       enabled: true
       docker_layer_caching: true
       resource_class: gpu.nvidia.small
-      image: ubuntu-1604-cuda-11.1:202012-01
+      image: ubuntu-2004-cuda-11.2:202103-01
 
     steps:
       - only_run_if_forked_pull_request

Dockerfile.arm

@@ -1,14 +1,17 @@
 # RedisAI Development Backends
 
-This document describes how a backend for RedisAI can be built, from this repository. It highlights the supported compilation devices on a per-backend basis, and highlights the tools and commands required.  Unless indicated otherwise, a backend is compiled in a docker, which is responsible for the configuration and installation of all tools required for a given backend on a per-platform basis.
+This document describes how ONNXRuntime backend can be built from this repository.
+We build the ONNXRuntime library with the DISABLE_EXTERNAL_INITIALIZERS=ON build flag. As a result, loading ONNX models that use external files to store the initial (usually very large) values of the model's operations, is invalid. Hence, initialization values must be part of the serialized model, which is also the standard use case.
+
+It is compiled in a docker, which is responsible for the configuration and installation of all tools required the build process.
 
 To follow these instructions, this repository must be cloned with all of its submodules (i.e *git clone --recursive https://github.com/redisai/redisai*)
 
-GNU Make is used as a runner for the dockerfile generator. Python is the language used for the generator script, and jinja is the templating library used to create the docker file from a template *dockerfile.tmpl* that can be found in the directory of a given backend listed below.
+GNU Make is used as a runner for the dockerfile generator. Python is the language used for the generator script, and jinja is the templating library used to create the docker file from the template *dockerfile.tmpl*, located in the `/opt/build/onnxruntime` directory.
 
-## Tools
+### Tools
 
-Building the backends requires installation of the following tools:
+Building the backend requires installation of the following tools:
 
 1. gnu make
 1. python (3.0 or higher)
@@ -21,17 +24,11 @@ On ubuntu bionic these can be installed by running the following steps, to insta
 sudo apt install python3 python3-dev make docker
 python3 -m venv /path/to/venv
 source /path/to/venv/bin/activate
-pip install jinja
+pip install jinja2
 ```
 
 -------
 
-## Backends
-
-### onnxruntime
-
-We build Onnxruntime library with DISABLE_EXTERNAL_INITIALIZERS=ON build flag. This means that loading ONNX models that use external files to store the initial (usually very large) values of the model's operations, is invalid. That is, initializers values must be part of the serialized model, which is also the standard use case.
-
 **Compilation target devices:**
 
 1. x86\_64 bit linux systems

Dockerfile.jetson

@@ -170,9 +170,16 @@ sudo ./opt/system-setup.py
 
 **Building**
 
-To compile RedisAI, run *make -C opt all*, from the root of the repository.
+Before compiling RedisAI module, make sure that you have the backends' shared libraries in the `deps` directory. These can be easily obtained by running:
+```./get_deps```
+or
+```./get_deps gpu```
+for having GPU support.
+Except for ONNXRuntime backend which is stored in a S3 bucket, other backends' binary files are downloaded directly from their official websites.
+Further details about building ONNXRuntime backend for RedisAI is described in [this document](developer-backends.md).
+
+To compile RedisAI, run `make -C opt` or `make -C opt GPU=1`, from the root of the repository. This will create the module's shared library `redisai.so` in `instali-cpu`/`install-gpu` directory respectively. 
 
-Build the backends is described in [this document](developer-backends.md).
 
 ### Testing