I'm a Beginner, there is some problem for me, someone can help me? thx ^_^

[grrrrr112]

when I run the python demo.py , OOM occurred like below:
RuntimeError: CUDA out of memory. Tried to allocate 44.00 MiB (GPU 0; 1.95 GiB total capacity; 1.23 GiB already allocated; 2.62 MiB free; 98.86 MiB cached)

so where is bitch_size?

thx ^_^

[lg920810]

In CornerNet.json,you should change both batch_size and chunk_sizes.For example, the batch_size is 30, the chunk_sizes is [15, 15]

[grrrrr112]

In CornerNet.json,you should change both batch_size and chunk_sizes.For example, the batch_size is 30, the chunk_sizes is [15, 15]

thx for your answer.^_^

my CornerNet.json is like below:

But it's still OOM T_T

"system": {
"dataset": "COCO",
"batch_size": 1,
"sampling_function": "cornernet",

    "train_split": "trainval",
    "val_split": "minival",

    "learning_rate": 0.00025,
    "decay_rate": 10,

    "val_iter": 100,

    "opt_algo": "adam",
    "prefetch_size": 5,

    "max_iter": 500000,
    "stepsize": 450000,
    "snapshot": 5000,

    "chunk_sizes": [15, 15],

    "data_dir": "./data"
}

[root@localhost CornerNet-Lite]# python3 demo.py
total parameters: 116969339
loading from /data/MachineLearning/CornerNet-Lite/core/../cache/nnet/CornerNet_Saccade/CornerNet_Saccade_500000.pkl
/usr/local/python3/lib/python3.7/site-packages/torch/nn/functional.py:2423: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
Traceback (most recent call last):
File "demo.py", line 10, in
bboxes = detector(image)
File "/data/MachineLearning/CornerNet-Lite/core/base.py", line 25, in call
bboxes = self._inference(image, *args, **kwargs)
File "/data/MachineLearning/CornerNet-Lite/core/base.py", line 21, in _inference
return self._func(self._db, self._nnet, image.copy(), *args, **kwargs)
File "/data/MachineLearning/CornerNet-Lite/core/test/cornernet_saccade.py", line 346, in cornernet_saccade_inference
dets, atts = decode_func(db, nnet, images, no_att=no_att)
File "/data/MachineLearning/CornerNet-Lite/core/test/cornernet_saccade.py", line 77, in batch_decode
test=True, num_dets=num_dets, no_border=True, no_att=no_att
File "/data/MachineLearning/CornerNet-Lite/core/nnet/py_factory.py", line 112, in test
return self.model(*xs, **kwargs)
File "/usr/local/python3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/data/MachineLearning/CornerNet-Lite/core/nnet/py_factory.py", line 30, in forward
return self.module(*xs, **kwargs)
File "/usr/local/python3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/data/MachineLearning/CornerNet-Lite/core/models/py_utils/modules.py", line 303, in forward
return self._test(*xs, **kwargs)
File "/data/MachineLearning/CornerNet-Lite/core/models/py_utils/modules.py", line 280, in _test
cnvs, ups = self.hg(image)
File "/usr/local/python3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/data/MachineLearning/CornerNet-Lite/core/models/py_utils/modules.py", line 234, in forward
inter = self.intersind
File "/usr/local/python3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/data/MachineLearning/CornerNet-Lite/core/models/py_utils/utils.py", line 194, in forward
return self.relu(bn2 + skip)
RuntimeError: CUDA out of memory. Tried to allocate 44.00 MiB (GPU 0; 1.95 GiB total capacity; 1.21 GiB already allocated; 20.62 MiB free; 75.49 MiB cached)
[root@localhost CornerNet-Lite]#

[lg920810]

How many GPU do you have? If you have just one, I think you can try set chunk_sizes=[1].

[grrrrr112]

How many GPU do you have? If you have just one, I think you can try set chunk_sizes=[1].

OOM T_T

But if I use debug mode to execute setp by setp, it can be done.

Maybe I should change my video card >_<

[root@localhost ~]# nvidia-smi
Tue May 7 20:31:20 2019
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 418.56 Driver Version: 418.56 CUDA Version: 10.1 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 750 Ti Off | 00000000:01:00.0 On | N/A |
| 38% 28C P8 1W / 38W | 222MiB / 1999MiB | 0% Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 12655 G /usr/bin/X 109MiB |
| 0 13192 G /usr/bin/gnome-shell 110MiB |
+-----------------------------------------------------------------------------+
[root@localhost ~]#