ajaycharan / resnet-tensorflow Goto Github PK

Implementation of ResNet in TensorFlow. Initialization from ImageNet pretrained weights is supported and this model has been successfully fine-tuned on different datasets.

##How to reproduce ImageNet results

• Download ImageNet dataset here. You will have to register in order to obtain permission.
• Point DATA_DIR in prepare_imagenet.py to the data directory and run data preparation. This will generate DATA_DIR/numpy/val_data.hdf5 file.

$ python prepare_imagenet.py

• Download model weights here. These weights were converted from original Caffe models using tensorpack converter from here.
• Configure paths to data and model weights in resnet_imagenet.py

MODEL_DEPTH=50
MODEL_PATH ='/home/kivan/datasets/pretrained/resnet/ResNet'+str(MODEL_DEPTH)+'.npy'
DATA_PATH = '/home/kivan/datasets/imagenet/ILSVRC2015/numpy/val_data.hdf5'

• Run evaluation:

$ python resnet_imagenet.py