Closed dingxm closed 1 year ago
Hi Milad4849, Thanks for your help. I used docker pull ghcr.io/bodenmillergroup/steinbock:latest-cellpose. I can use cellpose for the segmentation. However I got the error below,
Error segmenting objects in img/NBL_N0351.tiff: The following operation failed in the TorchScript interpreter. Traceback of TorchScript (most recent call last): File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/utils/mkldnn.py", line 64, in forward @torch.jit.script_method def forward(self, x): return torch.mkldnn_convolution(
x,
self.weight,
RuntimeError: could not create a primitive
Traceback (most recent call last):
File "/app/steinbock/steinbock/segmentation/cellpose.py", line 102, in try_segment_objects
masks, flows, styles, diams = model.eval(
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/models.py", line 216, in eval
diams, _ = self.sz.eval(x, channels=channels, channel_axis=channel_axis, invert=invert, batch_size=batch_size,
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/models.py", line 889, in eval
diam, diam_style = self.eval(x[i],
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/models.py", line 910, in eval
styles = self.cp.eval(x,
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/models.py", line 552, in eval
masks, styles, dP, cellprob, p = self._run_cp(x,
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/models.py", line 616, in _run_cp
yf, style = self._run_nets(img, net_avg=net_avg,
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/core.py", line 363, in _run_nets
y, style = self._run_net(img, augment=augment, tile=tile, tile_overlap=tile_overlap,
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/core.py", line 447, in _run_net
y, style = self.network(imgs, return_conv=return_conv)
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/core.py", line 315, in network
y, style = self.net(X)
File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/resnet_torch.py", line 202, in forward
T0 = self.downsample(data)
File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/resnet_torch.py", line 84, in forward
xd.append(self.down[n](y))
File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/steinbock-venv/lib/python3.8/site-packages/cellpose/resnet_torch.py", line 47, in forward
x = self.proj(x) + self.conv[1](self.conv[0](x))
File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/nn/modules/container.py", line 204, in forward
input = module(input)
File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript (most recent call last):
File "/opt/steinbock-venv/lib/python3.8/site-packages/torch/utils/mkldnn.py", line 64, in forward
@torch.jit.script_method
def forward(self, x):
return torch.mkldnn_convolution(
~~~~~~~~~~~~~~~~~~~~~~~~ <--- HERE
x,
self.weight,
RuntimeError: could not create a primitive
Any suggestion?
I am not certain but this can potentially be related to your CPU, what operating system, computer and CPU are you using?
The CPU is zen3 by AMD. Likely it is AMD CPU related problem. I will try the Intel CPU. Thanks
Hi I have tried to use the cellpose for the segmentation in steinbock:0.16.0. However only cellprofiler and deepcell are available. Thanks
$steinbock segment --help
Usage: steinbock segment [OPTIONS] COMMAND [ARGS]...
Perform image segmentation to create object masks
Options: --help Show this message and exit.
Commands: cellprofiler Segment objects in probability images using CellProfiler deepcell Run an object segmentation batch using DeepCell