Closed mgarbade closed 5 years ago
Thank you for your post. We noticed you have not filled out the following field in the issue template. Could you update them if they are relevant in your case, or leave them as N/A? Thanks. What is the top-level directory of the model you are using Have I written custom code OS Platform and Distribution TensorFlow installed from TensorFlow version Bazel version CUDA/cuDNN version GPU model and memory Exact command to reproduce
Sorry I was passing the also_save_raw_predictions
option wrongly.
# From tensorflow/models/research/
python deeplab/vis.py \
--logtostderr \
--vis_split="val" \
--model_variant="xception_65" \
--atrous_rates=6 \
--atrous_rates=12 \
--atrous_rates=18 \
--output_stride=16 \
--decoder_output_stride=4 \
--vis_crop_size=481 \
--vis_crop_size=641 \
--dataset="nyu" \
--checkpoint_dir=${PATH_TO_CHECKPOINT} \
--vis_logdir=${PATH_TO_VIS_DIR} \
--dataset_dir=${PATH_TO_DATASET} \
--also_save_raw_predictions=True
Is working!
Closing as this is resolved
When using the option
also_save_raw_predictions = True
option to output the inferred semantic segmentation maps, the resulting maps have different names than the original images. How can I fix that?They don't even map linearly to the original image names for some strange reason, so in my case (nyu_depth_v2 dataset) the test image with the original name NYU0001_0000.jpg gets mapped to the name
000326_prediction.png
. So I cannot run my own evaluation script on the extracted outputs.This was the command that I used: