AWS Neuron model outputs differs from Yolov5 - AWS Inferentia

[josebenitezg]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

No response

Question

Hi!

I was able to convert the model from yolov5 to neuron with the follow code:

import torch
import torch_neuron
from torchvision import models

model = torch.hub.load('yolo5',
        'custom',
        path='yolov5.pt',
        source='local',
        force_reload=True)  # local repo

fake_image = torch.zeros([1, 3, 640, 640], dtype=torch.float32)
#fake_image = (torch.rand(3), torch.rand(3))
try:
    torch.neuron.analyze_model(model, example_inputs=[fake_image])
except Exception:
    torch.neuron.analyze_model(model, example_inputs=[fake_image])

model_neuron = torch.neuron.trace(model, 
                                example_inputs=[fake_image])

## Export to saved model
model_neuron.save("model_converted.pt")

Now that I am trying to test and compare I have the tensors outputs different from yolo as follow:

Neuron Yolov5 Model:

[tensor([[-0.0356,  0.1790,  0.7456,  0.6292,  0.9359, 13.0000],
        [ 0.5830,  0.1404,  1.1279,  0.6628,  0.9359, 13.0000],
        [ 0.0823,  0.6350,  0.6272,  1.1599,  0.9315, 13.0000],
        [-0.1443,  0.1416,  0.2542,  0.5107,  0.9224, 13.0000],
        [ 0.3516,  0.6426,  0.7500,  1.0137,  0.9188, 13.0000],
        [ 0.3555,  0.1436,  0.7539,  0.5127,  0.9147, 13.0000]])]

Yolov5:

[tensor([[334.57495, 176.98302, 407.46155, 213.81169,   0.93721,  13.00000]])]

Inference script:

im = cv2.imread('test_img.jpg')
img0 = im.copy()
im = cv2.resize(im, (640, 640), interpolation = cv2.INTER_AREA)
# Convert
im = im.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
im = np.ascontiguousarray(im)
# Convert into torch
im = torch.from_numpy(im)
im = im.float()  # uint8 to fp16/32
im /= 255  # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
    im = im[None]  # expand for batch dim

# Load the compiled model
model = torch.jit.load('model_converted.pt')

# Inference
pred = model(im)
pred = non_max_suppression(pred) #nms function used same as yolov5 detect.py

#Process predictions
for i, det in enumerate(pred):  # per image
    im0 = img0.copy()
    color=(30, 30, 30)
    txt_color=(255, 255, 255)
    h_size, w_size = im.shape[-2:]
    print(h_size, w_size)
    lw = max(round(sum(im.shape) / 2 * 0.003), 2) 

    if len(det):
        # Write results
        for *xyxy, conf, cls in reversed(det):
            c = int(cls)  # integer class
            label = f'{CLASSES[c]} {conf:.2f}'
            print(label)
            box = xyxy 
            p1, p2 = (int(box[0]* w_size), int(box[1]* h_size)), (int(box[2]* w_size), int(box[3]* h_size))
            cv2.rectangle(im0, p1, p2, color, thickness=lw, lineType=cv2.LINE_AA)
            tf = max(lw - 1, 1)  # font thickness
            w, h = cv2.getTextSize(label, 0, fontScale=lw / 3, thickness=tf)[0]  # text width, height
            outside = p1[1] - h - 3 >= 0  # label fits outside box
            p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
            cv2.rectangle(im0, p1, p2, color, -1, cv2.LINE_AA)  # filled
            cv2.putText(im0,
                        label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2),
                        0,
                        lw / 3,
                        txt_color,
                        thickness=tf,
                        lineType=cv2.LINE_AA)
    # Save results (image with detections)
    status = cv2.imwrite('out.jpg', im0)

Is there something wrong when converting the model or running inference? The label and also the acc seems to be same as the expected, but tensors not.

I follow @jluntamazon pull but I not able to see difference. #2953

Environment

• Yolov5 latest
• Python 3.6.13
• AWS Inf1.large instance
• Ubuntu 18.05

Minimal Reproducible Example

No response

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[github-actions]

👋 Hello @josebenitezg, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[ooolox]

@glenn-jocher

[glenn-jocher]

@ooolox 👋 Hello! Thanks for asking about handling inference results. YOLOv5 🚀 PyTorch Hub models allow for simple model loading and inference in a pure python environment without using detect.py.

Simple Inference Example

This example loads a pretrained YOLOv5s model from PyTorch Hub as model and passes an image for inference. 'yolov5s' is the YOLOv5 'small' model. For details on all available models please see the README. Custom models can also be loaded, including custom trained PyTorch models and their exported variants, i.e. ONNX, TensorRT, TensorFlow, OpenVINO YOLOv5 models.

import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, etc.
# model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt')  # custom trained model

# Images
im = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, URL, PIL, OpenCV, numpy, list

# Inference
results = model(im)

# Results
results.print()  # or .show(), .save(), .crop(), .pandas(), etc.

results.xyxy[0]  # im predictions (tensor)
results.pandas().xyxy[0]  # im predictions (pandas)
#      xmin    ymin    xmax   ymax  confidence  class    name
# 0  749.50   43.50  1148.0  704.5    0.874023      0  person
# 2  114.75  195.75  1095.0  708.0    0.624512      0  person
# 3  986.00  304.00  1028.0  420.0    0.286865     27     tie

See YOLOv5 PyTorch Hub Tutorial for details.

Good luck 🍀 and let us know if you have any other questions!

[ooolox]

Hi @glenn-jocher, thanks for your response.

The custom Neuron Yolov5 inference script we used gives us results like this
[tensor([[-0.0356, 0.1790, 0.7456, 0.6292, 0.9359, 13.0000], [ 0.5830, 0.1404, 1.1279, 0.6628, 0.9359, 13.0000], [ 0.0823, 0.6350, 0.6272, 1.1599, 0.9315, 13.0000], [-0.1443, 0.1416, 0.2542, 0.5107, 0.9224, 13.0000], [ 0.3516, 0.6426, 0.7500, 1.0137, 0.9188, 13.0000], [ 0.3555, 0.1436, 0.7539, 0.5127, 0.9147, 13.0000]])]

which is not similar to the results from the yolov5 model
[tensor([[334.57495, 176.98302, 407.46155, 213.81169, 0.93721, 13.00000]])]

can you take a look at it?

[ooolox]

Hi aws-zejdaj, could you check this out.

[josebenitezg]

hi @jluntamazon did you know what else could be?

[jluntamazon]

The torch hub version of yolov5 does not directly expose the inplace flag that was added in #2953 at the API level. This flag is used to replace the in-place operations for torch-neuron compatibility. It is possible to set this manually on the submodules of the underlying model:

import torch
import torch_neuron

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s')

# Configure to use inplace flag for Neuron
for m in model.modules():
    if hasattr(m, 'inplace'):
        m.inplace = False

# Trace with Neuron
example = torch.zeros((1, 3, 384, 640), dtype=torch.float)
model.model(example) # Execute once to avoid trace errors
trace = torch_neuron.trace(model.model, (example,))

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

[fishuke]

@josebenitezg your problem is here:

p1, p2 = (int(box[0]* w_size), int(box[1]* h_size)), (int(box[2]* w_size), int(box[3]* h_size))

Remove this line and it will work.