chwilms / attentionmask Goto Github PK

Hi there, I successfully followed the instructions up until the "Inference stage". Here, I attempted to generate proposals for the COCO dataset by using the command provided in the READ.Me. Upon doing so I got the following error:

loading annotations into memory...
Done (t=3.57s)
creating index...
index created!
Progress: |--------------------------------------------------| 0.0% CompleteF0226 17:52:22.489114 3020 syncedmem.cpp:56] Check failed: error == cudaSuccess (2 vs. 0) out of memory
*** Check failure stack trace: ***
Aborted (core dumped)

I am currently running the following:

• Ubuntu 18.04
• Open CV 3.2
• Python 2.7
• Cuda 9.0 (followed these instructions for installation https://gist.github.com/Mahedi-61/2a2f1579d4271717d421065168ce6a73)
• GPU - GTX 1060 6GB

Any help would be appreciated, thanks in advance.

I had finally got the model training but I have now begun getting the following two errors and I'm unsure as to why.

Snapshotting to binary proto file params/attentionMask-8-128_iter_50.caffemodel
I0304 23:27:38.113571 4767 sgd_solver.cpp:273] Snapshotting solver state to binary proto file params/attentionMask-8-128_iter_50.solverstate
F0304 23:27:40.473143 4767 syncedmem.hpp:31] Check failed: error == cudaSuccess (29 vs. 0) driver shutting down
*** Check failure stack trace: ***
./train.sh: line 26: 4767 Aborted (core dumped) python trainAttentionMask.py 0 attentionMask-8-128 --init_weights resnet-50-model.caffemodel --step $SIZE_EPOCH

double free or corruption (!prev)
./train.sh: line 26: 5032 Aborted (core dumped) python testAttentionMask.py 0 attentionMask-8-128 --init_weights attentionMask-8-128_iter_$STEP.caffemodel --dataset train2014

When running the trainAttentionMask.py by itself I keep getting the following error.

I0302 01:16:14.811571 3437 sgd_solver.cpp:106] Iteration 0, lr = 0.0001
Traceback (most recent call last):
File "trainAttentionMask.py", line 88, in
solver.step(args.step)
File "/home/hamzah/Documents/AttentionMask/python_layers/data/boxSelectionLayerMP.py", line 107, in reshape
self.item, self.zoom_negtive_samples,self.shift_negtive_samples,i =conn.recv()
EOFError

When looking online I have found the EOF error is the following -

When the input() function is interrupted in both Python 2.7 and Python 3.6+, or when input() reaches the end of a file unexpectedly in Python 2.7.

Any help would be appreciated, thanks in advance

Hi there, i'm new to the computer vision scene, and was wondering if i could get more information on how to use you model. I am currently working on strawberry detection in fields, and with strawberry's being fairly small, your model caught my attention. I was wondering if this would be problem solvable by your model. I know issues should not be used like this, so is there anyway I can get in contact with you.

Thanks in advance.