Step 02: Detecting Objects Using resnet50

This tutorial and the assets can be downloaded as part of the Wallaroo Tutorials repository.

Step 02: Detecting Objects Using resnet50

The following tutorial demonstrates how to use a trained mobilenet model deployed in Wallaroo to detect objects. This process will use the following steps:

  1. Create a Wallaroo workspace and pipeline.
  2. Upload a trained resnet50 ML model and add it as a pipeline step.
  3. Deploy the pipeline.
  4. Perform an inference on a sample image.
  5. Draw the detected objects, their bounding boxes, their classifications, and the confidence of the classifications on the provided image.
  6. Review our results.


Import Libraries

The first step will be to import our libraries. Please check with Step 00: Introduction and Setup and verify that the necessary libraries and applications are added to your environment.

import torch
import pickle
import wallaroo
from wallaroo.object import EntityNotFoundError
from wallaroo.framework import Framework

import numpy as np
import json
import requests
import time
import pandas as pd
from CVDemoUtils import CVDemo

# used to display dataframe information without truncating
from IPython.display import display
import pandas as pd
pd.set_option('display.max_colwidth', None)

# used for unique connection names

import string
import random
suffix= ''.join(random.choice(string.ascii_lowercase) for i in range(4))

Connect to the Wallaroo Instance

The first step is to connect to Wallaroo through the Wallaroo client. The Python library is included in the Wallaroo install and available through the Jupyter Hub interface provided with your Wallaroo environment.

This is accomplished using the wallaroo.Client() command, which provides a URL to grant the SDK permission to your specific Wallaroo environment. When displayed, enter the URL into a browser and confirm permissions. Store the connection into a variable that can be referenced later.

If logging into the Wallaroo instance through the internal JupyterHub service, use wl = wallaroo.Client(). For more information on Wallaroo Client settings, see the Client Connection guide.

# Login through local service

wl = wallaroo.Client()

Set Variables

The following variables and methods are used later to create or connect to an existing workspace, pipeline, and model. This example has both the resnet model, and a post process script.

workspace_name = f'resnetworkspace{suffix}'
pipeline_name = f'resnetnetpipeline{suffix}'
model_name = f'resnet50{suffix}'
model_file_name = 'models/'
def get_workspace(name):
    workspace = None
    for ws in wl.list_workspaces():
        if == name:
            workspace= ws
    if(workspace == None):
        workspace = wl.create_workspace(name)
    return workspace

def get_pipeline(name):
        pipeline = wl.pipelines_by_name(name)[0]
    except EntityNotFoundError:
        pipeline = wl.build_pipeline(name)
    return pipeline

Create Workspace

The workspace will be created or connected to, and set as the default workspace for this session. Once that is done, then all models and pipelines will be set in that workspace.

workspace = get_workspace(workspace_name)
{'name': 'resnetworkspaceejdf', 'id': 16, 'archived': False, 'created_by': '4e296632-35b3-460e-85fe-565e311bc566', 'created_at': '2023-07-14T15:16:00.093465+00:00', 'models': [], 'pipelines': []}

Create Pipeline and Upload Model

We will now create or connect to an existing pipeline as named in the variables above.

pipeline = get_pipeline(pipeline_name)

resnet_model = wl.upload_model(model_name, model_file_name, framework=Framework.ONNX).configure(batch_config="single")

Deploy Pipeline

With the model uploaded, we can add it is as a step in the pipeline, then deploy it. Once deployed, resources from the Wallaroo instance will be reserved and the pipeline will be ready to use the model to perform inference requests.

name resnetnetpipelineejdf
created 2023-07-14 15:16:02.616654+00:00
last_updated 2023-07-14 15:16:02.616654+00:00
deployed (none)
versions 3a75189a-d406-4377-a762-a16fb1464cec
name resnetnetpipelineejdf
created 2023-07-14 15:16:02.616654+00:00
last_updated 2023-07-14 15:16:51.888236+00:00
deployed True
versions 5c9b6b1f-43e0-4db9-a469-7f00fbf75dee, 3a75189a-d406-4377-a762-a16fb1464cec
steps resnet50ejdf

Test the pipeline by running inference on a sample image

Prepare input image

Next we will load a sample image and resize it to the width and height required for the object detector.

We will convert the image to a numpy ndim array and add it do a dictionary

#The size the image will be resized to
width = 640
height = 480

cvDemo = CVDemo()

imagePath = 'data/images/input/example/dairy_bottles.png'

# The image width and height needs to be set to what the model was trained for.  In this case 640x480.
tensor, resizedImage = cvDemo.loadImageAndResize(imagePath, width, height)

# get npArray from the tensorFloat
npArray = tensor.cpu().numpy()

dictData = {"tensor":[npArray]}
dataframedata = pd.DataFrame(dictData)

Run Inference

With that done, we can have the model detect the objects on the image by running an inference through the pipeline, and storing the results for the next step.

IMPORTANT NOTE: If necessary, add timeout=60 to the infer method if more time is needed to upload the data file for the inference request.

startTime = time.time()
# pass the dataframe in 
infResults = pipeline.infer(dataframedata, dataset=["*", "metadata.elapsed"])
endTime = time.time()

Draw the Inference Results

With our inference results, we can take them and use the Wallaroo CVDemo class and draw them onto the original image. The bounding boxes and the confidence value will only be drawn on images where the model returned a 50% confidence rate in the object’s identity.

df = pd.DataFrame(columns=['classification','confidence','x','y','width','height'])
pd.options.mode.chained_assignment = None  # default='warn'
pd.options.display.float_format = '{:.2%}'.format

# Points to where all the inference results are
boxList = infResults.loc[0]["out.output"]

# # reshape this to an array of bounding box coordinates converted to ints

boxA = np.array(boxList)
boxes = boxA.reshape(-1, 4)
boxes = boxes.astype(int)

df[['x', 'y','width','height']] = pd.DataFrame(boxes)

classes = infResults.loc[0]["out.3070"]
confidences = infResults.loc[0]["out.3069"]

infResults = {
    'model_name' : model_name,
    'pipeline_name' : pipeline_name,
    'width': width,
    'height': height,
    'image' : resizedImage,
    'boxes' : boxes,
    'classes' : classes,
    'confidences' : confidences,
    'confidence-target' : 0.90,
    'inference-time': (endTime-startTime),
    'onnx-time' : int(infResults.loc[0]["metadata.elapsed"][1]) / 1e+9,                

image = cvDemo.drawAndDisplayDetectedObjectsWithClassification(infResults)

Extract the Inference Information

To show what is going on in the background, we’ll extract the inference results create a dataframe with columns representing the classification, confidence, and bounding boxes of the objects identified.

idx = 0 
for idx in range(0,len(classes)):
    cocoClasses = cvDemo.getCocoClasses()
    df['classification'][idx] = cocoClasses[classes[idx]] # Classes contains the 80 different COCO classificaitons
    df['confidence'][idx] = confidences[idx]
classification confidence x y width height
0 bottle 99.65% 2 193 76 475
1 bottle 98.83% 610 98 639 232
2 bottle 97.00% 544 98 581 230
3 bottle 96.96% 454 113 484 210
4 bottle 96.48% 502 331 551 476
... ... ... ... ... ... ...
95 bottle 5.72% 556 287 580 322
96 refrigerator 5.66% 80 161 638 480
97 bottle 5.60% 455 334 480 349
98 bottle 5.46% 613 267 635 375
99 bottle 5.37% 345 2 395 99

100 rows × 6 columns

Undeploy the Pipeline

With the inference complete, we can undeploy the pipeline and return the resources back to the Wallaroo instance.

name resnetnetpipelineejdf
created 2023-07-14 15:16:02.616654+00:00
last_updated 2023-07-14 15:16:51.888236+00:00
deployed False
versions 5c9b6b1f-43e0-4db9-a469-7f00fbf75dee, 3a75189a-d406-4377-a762-a16fb1464cec
steps resnet50ejdf