Skip to content

Latest commit

 

History

History
54 lines (38 loc) · 1.13 KB

File metadata and controls

54 lines (38 loc) · 1.13 KB

Dog Breed Prediction

Accuracy

About data set

The dog breed dataset consists of 133 different breeds

  • Data

  • Download data and unzip:

$ wget https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/dogImages.zip

$ unzip dogImages.zip

Training

  • Clone project
$ git clone https://github.com/DucLeTrong/dog_breed_classification

$ cd dog_breed_classification
  • Install requirements
$ pip3 install -r requirements.txt
  • Train model
$ python3 train.py 

Test model

$ python3 test.py 

Inference

$ python3 infer.py --img_path='2.jpg' --model_path='model.pt'
  • If a dog is detected in the image, return the predicted breed.

png

  • If a human is detected in the image, return the resembling dog breed.

png

png

  • If neither is detected in the image, provide output that indicates an error.