IndexError: list index out of range

[leewonjiin]

  bash examples/train_lsp_alexnet_imagenet.sh 

Elapsed time for finding uninitialized variables: 0.42s Elapsed time to init them: 0.16s args.resume: False args.snapshot: /home/wonjinlee/deeppose/weights/bvlc_alexnet.tf Reading dataset from /home/wonjinlee/data/lsp/train_joints.csv 0it [00:00, ?it/s] Traceback (most recent call last): File "/home/wonjinlee/deeppose/scripts/train.py", line 233, in main(sys.argv[1:]) File "/home/wonjinlee/deeppose/scripts/train.py", line 168, in main downscale_height=args.downscale_height File "/home/wonjinlee/deeppose/scripts/dataset.py", line 37, in init self.load_images() File "/home/wonjinlee/deeppose/scripts/dataset.py", line 129, in load_images print('Joints shape:', self.joints[0][1].shape) IndexError: list index out of range

How could I deal with this kind of error?

[asanakoy]

@leewonjiin check what is inside variable self.joints. self.joints must be a lsit of pairs (image_id, joints). Looks like joints are not properly read from disk (empty list).

[leewonjiin]

Okay, I have another question. I tried to train mpii datasets, and it runs well for a while, but it show error messages like this

Traceback (most recent call last): File "examples/train_mpii_alexnet_scratch.py", line 46, in scripts.train.main(argv) File "/home/wonjinlee/deeppose/scripts/train.py", line 228, in main output_dir=args.o_dir File "/home/wonjinlee/deeppose/scripts/train.py", line 73, in train_loop tag_prefix='test') File "/home/wonjinlee/deeppose/scripts/regressionnet.py", line 321, in evaluate_pcp metric_name='PCP') File "/home/wonjinlee/deeppose/scripts/regressionnet.py", line 225, in calculate_metric gt_joints = convert2canonical(gt_joints) File "/home/wonjinlee/deeppose/poseevaluation/lsp.py", line 88, in convert2canonical assert joints.shape[1:] == (14, 2), 'LSP must contain 14 joints per person' AssertionError: LSP must contain 14 joints per person

Is this means I should train lsp dataset first?

[asanakoy]

This means that either the lsp dataset was changed and has more joint than before or the data is corrupted. Every person must have exactly 14 joints.

[leewonjiin]

I think variable of self.joints is right.

        self.joints.append((image_id, joints))
        self.info.append((is_valid_joints, bbox))
    print('Joints shape:', self.joints[0][1].shape)

[asanakoy]

Closed due to the lack of activity