Git Product home page Git Product logo

mono-depth's Introduction

mono-depth

Experiments with learning depth from a single image for course project.

Details and history in presentation here: https://docs.google.com/presentation/d/1GZkUPq5xFVHfjKiVrPzIXjKb_lBb_r4KPjPVz_VMwK8/edit?usp=sharing

Example Results:

hallway tree

data

I used data from the Make3d Dataset found here: http://make3d.cs.cornell.edu/data.html

I organized the data as follows: The test and training data were downloaded to a directory called "data" and then into subdirectories:

../data/test/depthmaps

http://www.cs.cornell.edu/~asaxena/learningdepth/Data/Dataset2_Depths.tar.gz

../data/test/images

http://cs.stanford.edu/people/asaxena/learningdepth/Data/Dataset2_Images.tar.gz

../data/train/depthmaps

http://cs.stanford.edu/people/asaxena/learningdepth/Data/Dataset3_Depths.tar.gz

../data/train/images

http://www.cs.cornell.edu/~asaxena/learningdepth/Data/Dataset3_Images.tar.gz

After downloading and extracting the data to the appropriate paths, I rotated the images (they are originally flipped 90 degrees from the depthmaps and resized them to make the model train more quickly with the following commands:

sh resize_and_rotate.sh ../data/train/images/ ../data/train/small_images/

sh resize_and_rotate.sh ../data/test/images/ ../data/test/small_images/

install

conda env create -f mono_environment.yml

run

To run with debug statements on cpu:

THEANO_FLAGS="device=cpu,optimizer=None,compute_test_value=raise,floatX=float32" python predict_depth.py

To run on cpu:

THEANO_FLAGS="device=cpu,floatX=float32" python predict_depth.py

To run on gpu with no debug:

THEANO_FLAGS="device=gpu,floatX=float32" python predict_depth.py

bugs

Error in bottom few rows of pixels

mono-depth's People

Contributors

johannah avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar

Forkers

gongenhao jmideamaker johndpope topworld2040 rzel liyancas hyzcn paman-ninja afcarl

mono-depth's Issues

Memory error: Theano cache?

Hi,

I'm trying to test this wonderful code, but I have got some problems probably on theano memory chache. I have just clean my theano cache deleting the folder manually, but it doesn't resolve my issues. I would report my traceback.
Someone could help me?

Best,
Goffredo

Using gpu device 0: GeForce GT 740M (CNMeM is enabled with initial size: 80.0% of memory, cuDNN 5105)
Searching for images in path: C:\deep_learning\mono-depth-master\mono-depth-master\data\small_images*.jpg
Searching for depthmaps in path: C:\deep_learning\mono-depth-master\mono-depth-master\data\depthmaps*.mat
FOUND 473 matching images and depths
Using 460 images
loading 20 images and depthmaps
coarse_pool1 SHAPE str = [ 20 32 113 85]
coarse_pool2 SHAPE str = [20 64 56 42]
coarse_depool1 SHAPE str = [ 20 512 224 168]
log_thunk_trace: There was a problem executing an Op.
Traceback (most recent call last):
File "predict_depth.py", line 100, in
updates = adam(train_loss, params, learning_rate=1E-4)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\lasagne\updates.py", line 583, in adam
all_grads = get_or_compute_grads(loss_or_grads, params)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\lasagne\updates.py", line 123, in get_or_compute_grads
return theano.grad(loss_or_grads, params)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 555, in grad
grad_dict, wrt, cost_name)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1317, in _populate_grad_dict
rval = [access_grad_cache(elem) for elem in wrt]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1317, in
rval = [access_grad_cache(elem) for elem in wrt]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in access_term_cache
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 967, in
output_grads = [access_grad_cache(var) for var in node.outputs]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1272, in access_grad_cache
term = access_term_cache(node)[idx]
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gradient.py", line 1108, in access_term_cache
new_output_grads)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gof\op.py", line 700, in L_op
return self.grad(inputs, output_grads)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\tensor\basic.py", line 2923, in grad
gx = gz.sum(axis=axis + axis_broadcasted)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\tensor\var.py", line 634, in sum
acc_dtype=acc_dtype)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\tensor\basic.py", line 3067, in sum
out = elemwise.Sum(axis=axis, dtype=dtype, acc_dtype=acc_dtype)(input)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gof\op.py", line 663, in call
required = thunk()
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gof\op.py", line 832, in rval
fill_storage()
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\theano\gof\cc.py", line 1698, in call
reraise(exc_type, exc_value, exc_trace)
File "C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\six.py", line 686, in reraise
raise value
MemoryError: None

KeyError: DepthMap

Hi I have some problems related to predict_depth.py.
I don't know what is loadmat function and it gives me these errors.
Someone could help me?

Best
Goffredo

C:\deep_learning\mono-depth-master\mono-depth-master>python predict_depth.py
WARNING (theano.sandbox.cuda): The cuda backend is deprecated and will be removed in the next release (v0.10). Please switch to the gpuarray backend. You can get more information about how to switch at this URL:
https://github.com/Theano/Theano/wiki/Converting-to-the-new-gpu-back-end%28gpuarray%29

Using gpu device 0: GeForce GT 740M (CNMeM is enabled with initial size: 80.0% of memory, cuDNN 5105)
Searching for images in path: C:\deep_learning\mono-depth-master\mono-depth-master\data\small_images*.jpg
Searching for depthmaps in path: C:\deep_learning\mono-depth-master\mono-depth-master\data\depthmaps*.mat
FOUND 5 matching images and depths
Using 3 images
loading 3 images and depthmaps
C:\deep_learning\WinPython-64bit-3.4.4.4Qt5\python-3.4.4.amd64\lib\site-packages\scipy\io\matlab\mio.py:136: MatReadWarning: Duplicate variable name "None" in stream - replacing previous with new
Consider mio5.varmats_from_mat to split file into single variable files
matfile_dict = MR.get_variables(variable_names)
Traceback (most recent call last):
File "predict_depth.py", line 40, in
dmaps[0:minibatchsize])
File "C:\deep_learning\mono-depth-master\mono-depth-master\utils.py", line 53, in load_data
depf = loadmat(dmaps[xx])['depthMap']
KeyError: 'depthMap'

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.