Deeplab v3+ Shape mismatch in tuple component

Question

I have trained deeplab v3+ on ADE20Kdataset,and got the trained ckptjlogs and eventslogs.But when I run eval.pyand vis.pyon ADE20K,I got the following errors about shape:

Shape mismatch in tuple component 1. Expected [513,513,3], got [513,683,3]

These are my evalscripts and vis scripts:

evalscripts:

#!/bin/bash

cd ../

python deeplab/eval.py  \
--logtostderr \
--eval_split="val" \
--model_variant="xception_65" \
--atrous_rates=6 \
--atrous_rates=12 \
--atrous_rates=18 \
--output_stride=16 \
--decoder_output_stride=4 \
--eval_crop_size=513 \
--eval_crop_size=513 \
--checkpoint_dir=deeplab/datasets/ADE20K/exp/train_on_train_set/train/  \
--eval_logdir=deeplab/datasets/ADE20K/exp/train_on_train_set/eval/  \
--dataset_dir=deeplab/datasets/ADE20K/tfrecord/ \
--max_number_of_iterations=1

visscripts:

#!/bin/bash

cd ../

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=513 \
--vis_crop_size=513 \
--checkpoint_dir=deeplab/datasets/ADE20K/exp/train_on_train_set/train/  \
--vis_logdir=deeplab/datasets/ADE20K/exp/train_on_train_set/vis/  \
--dataset_dir=deeplab/datasets/ADE20K/tfrecord/ \
--max_number_of_iterations=1

And my trainscripts:

#!/bin/bash

cd ../

python deeplab/train.py  \
--logtostderr  \
--training_number_of_steps=150000  \
--train_split="train"  \
--model_variant="xception_65"  \
--atrous_rates=6  \
--atrous_rates=12  \
--atrous_rates=18  \
--output_stride=16  \
--decoder_output_stride=4  \
--train_crop_size=513  \
--train_crop_size=513  \
--train_batch_size=2  \
--min_resize_value=513  \
--max_resize_value=513  \
--resize_factor=16  \
--dataset="ade20k"  \
 --tf_initial_checkpoint=deeplab/datasets/ADE20K/init_models        /deeplabv3_xception_ade20k_train/model.ckpt.index  \
--train_logdir=deeplab/datasets/ADE20K/exp/train_on_train_set/train  \
--dataset_dir=deeplab/datasets/ADE20K/tfrecord/

Is there any thing I set wrong? Thanks for any help.

score 0 · Answer 1 · answered Oct 14 '19 at 08:42

Make sure the arguments used in your sh-script match the arguments required by your current code version.

Not long ago you had to pass two separated values for the crop size buy the current implementation uses

--eval_crop_size="513,513" \

or

 --vis_crop_size="513,513" \

(taken from here)

Hope this helps ;). If not try to print the crop values in the vis.py/eval.py script and look if the are passed correctly.

Deeplab v3+ Shape mismatch in tuple component

1 Answers1