Another attempt, I installed tensorflow-gpu 1.6.0 for CUDA library 8.0 but still running python inference.py --img-path=./input/outdoor_1.png --dataset=ade20k --filter-scale=2 --model=others

generates "no checkpoint file found" and the results are not he same as the one stated here.

from icnet-tensorflow.

Hey @aliericcantona, it seems that the checkpoint is missing, so you cannot load the pre-trained weights. You can refer to #45.

from icnet-tensorflow.

change checkpoints.txt to checkpoints

from icnet-tensorflow.

thanks it works. Actually checkpoint.txt --> checkpoint

from icnet-tensorflow.

the results are not exactly the same as the one you posted just slightly different (may be because of the slightly trained model difference). The color model (labels) are exactly the same as PSPNET ADE20K or different?

from icnet-tensorflow.

@aliericcantona, I have updated the model but the output results not, so the results would be a little different.

from icnet-tensorflow.

If you want to apply to other datasets, change following four lines

IGNORE_LABEL = 255 # The class number of background
INPUT_SIZE = '720, 720' # Input size for training

BATCH_SIZE = 16
LEARNING_RATE = 1e-3
MOMENTUM = 0.9
NUM_CLASSES = 19
NUM_STEPS = 60001
POWER = 0.9
RANDOM_SEED = 1234
WEIGHT_DECAY = 0.0001
PRETRAINED_MODEL =
SNAPSHOT_DIR = './snapshots/'
SAVE_NUM_IMAGES = 4
SAVE_PRED_EVERY = 50

these codes in train.py，in model file has ade20k weights,but failed to train, PRETRAINED_MODEL how to load ,PRETRAINED_MODEL = ?

from icnet-tensorflow.