dmlc/gluon-cv

How to use a trained params to predict?

Open

#229 opened on Aug 2, 2018

View on GitHub
 (9 comments) (0 reactions) (0 assignees)Python (1,224 forks)batch import
good first issuequestion

Repository metrics

Stars
 (5,610 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Hi. I am a new one here. It is a awesome lib for CV, thanks for your great work. Now, I am encountering a problem that I trained ssd_300_vgg16_atrous_voc on my own dataset, the dataset has 4 classes. After training, I got a "ssd_300_vgg16_atrous_voc_best.params" file. When I want to load the parmeters and predict on new images, it return an error, logs as it, AssertionError: Failed loading Parameter 'ssd0_convpredictor4_conv0_weight' from saved params: shape incompatible expected (126, 0, 3, 3) vs saved (30, 512, 3, 3) The command I used as follow, from gluoncv import model_zoo, data, utils from matplotlib import pyplot as plt import mxnet as mx ctx = [mx.cpu()] net = model_zoo.get_model('ssd_300_vgg16_atrous_voc', pretrained=False) net.load_parameters('ssd_300_vgg16_atrous_voc_best.params', ctx = ctx)

Thanks for any help.

Contributor guide

Research direction
The error indicates a shape mismatch because the pretrained model 'ssd 300 vgg16 atrous voc' expects 21 classes (20 VOC + background) but your trained model has 5 classes (4 + background). To load your custom parameters, you need to create the model with the correct number of classes: net = model zoo.get model('ssd 300 vgg16 atrous voc', pretrained=False, classes=5) before loading the saved params.
Tech stack
python
Domain
machine learningcomputer vision
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonMXNetGluonCV
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70