How to get [gt_depthmap] ?
Hi yoyo, I'm having a hard time learning. You say, I need [reference_image, source_images, reference_camera, source_cameras, reference_gt_depthmap].
So I had preapare COLMAP dataset.


image size 3072 X 2304
This datases is COLMAP data set.
But When I check DTU dataset, That is consist of [depth map .pfm] and [depth visual .png],
So, How can i get depth visual file ?
I could use rainbow depth map with your visualize.py
But Error.
How can I do...
Is my preparation correct?
2019-08-08 15:45:23.672483: W tensorflow/core/framework/op_kernel.cc:1198] Unknown: exceptions.AttributeError: 'NoneType' object has no attribute 'astype' 2019-08-08 15:45:23.672576: W tensorflow/core/framework/op_kernel.cc:1198] Unknown: exceptions.AttributeError: 'NoneType' object has no attribute 'astype' [[Node: PyFunc = PyFunc[Tin=[DT_INT64], Tout=[DT_FLOAT, DT_FLOAT, DT_FLOAT], token="pyfunc_1"](arg0)]] Traceback (most recent call last): File "/home/git/MVSNet-master/mvsnet/train.py", line 356, in <module> tf.app.run() File "/home/git/anaconda2/envs/train.py/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 124, in run _sys.exit(main(argv)) File "/home/git/MVSNet-master/mvsnet/train.py", line 351, in main train(sample_list) File "/home/git/MVSNet-master/mvsnet/train.py", line 316, in train [summary_op, train_opt, loss, less_one_accuracy, less_three_accuracy]) File "/home/git/anaconda2/envs/train.py/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run run_metadata_ptr) File "/home/git/anaconda2/envs/train.py/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1128, in _run feed_dict_tensor, options, run_metadata) File "/home/git/anaconda2/envs/train.py/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1344, in _do_run options, run_metadata) File "/home/git/anaconda2/envs/train.py/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1363, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.UnknownError: exceptions.AttributeError: 'NoneType' object has no attribute 'astype' [[Node: PyFunc = PyFunc[Tin=[DT_INT64], Tout=[DT_FLOAT, DT_FLOAT, DT_FLOAT], token="pyfunc_1"](arg0)]] [[Node: Model_tower0/IteratorGetNext = IteratorGetNext[output_shapes=[<unknown>, <unknown>, <unknown>], output_types=[DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](Iterator)]]
There is no GT depth map unless you use the laser scan to acquire the ground truth point cloud.