vanvalenlab / deepcell-retinamask Goto Github PK
View Code? Open in Web Editor NEWRetinaNet and RetinaMask models for object detection based on TensorFlow and DeepCell-tf.
License: Other
RetinaNet and RetinaMask models for object detection based on TensorFlow and DeepCell-tf.
License: Other
Hi author @willgraf
I have an error when training:
No module named 'deepcell_retinamask.callbacks'
I have installed deepcell-retinamask with
$ pip install deepcell-retinamask
Can you help me how to fix this.
Thank you very much
Hi,
Thank for this very interesting package.
I have modified a little bit your notebook to use multiclass mask, everything seems to work properly but once I try to fit the model I have this error:
Training on 1 GPUs.
Epoch 1/10
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/indexed_slices.py:449: UserWarning: Converting sparse IndexedSlices(IndexedSlices(indices=Tensor("gradient_tape/mask_loss/cond/gradients/mask_loss/cond/map/while_grad/gradients/mask_loss/cond/map/while/GatherNd_grad/Squeeze:0", shape=(None,), dtype=int64), values=Tensor("gradient_tape/mask_loss/cond/gradients/mask_loss/cond/map/while_grad/gradients/AddN_3:0", shape=(None, None), dtype=float32), dense_shape=Tensor("mask_loss/cond/map/while/gradient_tape/mask_loss/cond/gradients/mask_loss/cond/map/while_grad/gradients/mask_loss/cond/map/while/GatherNd_grad/Shape:0", shape=(2,), dtype=int64))) to a dense Tensor of unknown shape. This may consume a large amount of memory.
"shape. This may consume a large amount of memory." % value)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/indexed_slices.py:449: UserWarning: Converting sparse IndexedSlices(IndexedSlices(indices=Tensor("gradient_tape/mask_loss/cond/gradients/mask_loss/cond/map/while_grad/gradients/mask_loss/cond/map/while/GatherNd_1_grad/Squeeze:0", shape=(None,), dtype=int64), values=Tensor("gradient_tape/mask_loss/cond/gradients/mask_loss/cond/map/while_grad/gradients/mask_loss/cond/map/while/transpose_grad/transpose:0", shape=(None, 28, 28, None), dtype=float32), dense_shape=Tensor("mask_loss/cond/map/while/gradient_tape/mask_loss/cond/gradients/mask_loss/cond/map/while_grad/gradients/mask_loss/cond/map/while/GatherNd_1_grad/Shape:0", shape=(4,), dtype=int64))) to a dense Tensor of unknown shape. This may consume a large amount of memory.
"shape. This may consume a large amount of memory." % value)
WARNING:tensorflow:Gradients do not exist for variables ['conv_0_semantic_upsample_2/kernel:0', 'conv_0_semantic_upsample_2/bias:0', 'conv_0_semantic_upsample_3/kernel:0', 'conv_0_semantic_upsample_3/bias:0', 'conv_0_semantic_upsample_4/kernel:0', 'conv_0_semantic_upsample_4/bias:0', 'conv_0_semantic_upsample_5/kernel:0', 'conv_0_semantic_upsample_5/bias:0', 'conv_0_semantic_upsample_6/kernel:0', 'conv_0_semantic_upsample_6/bias:0', 'conv_0_semantic_2/kernel:0', 'conv_0_semantic_2/bias:0', 'conv_0_semantic_3/kernel:0', 'conv_0_semantic_3/bias:0', 'conv_0_semantic_4/kernel:0', 'conv_0_semantic_4/bias:0', 'conv_0_semantic_5/kernel:0', 'conv_0_semantic_5/bias:0', 'conv_0_semantic_6/kernel:0', 'conv_0_semantic_6/bias:0', 'batch_normalization_0_semantic_2/gamma:0', 'batch_normalization_0_semantic_2/beta:0', 'batch_normalization_0_semantic_3/gamma:0', 'batch_normalization_0_semantic_3/beta:0', 'batch_normalization_0_semantic_4/gamma:0', 'batch_normalization_0_semantic_4/beta:0', 'batch_normalization_0_semantic_5/gamma:0', 'batch_normalization_0_semantic_5/beta:0', 'batch_normalization_0_semantic_6/gamma:0', 'batch_normalization_0_semantic_6/beta:0', 'conv_1_semantic_2/kernel:0', 'conv_1_semantic_2/bias:0', 'conv_1_semantic_3/kernel:0', 'conv_1_semantic_3/bias:0', 'conv_1_semantic_4/kernel:0', 'conv_1_semantic_4/bias:0', 'conv_1_semantic_5/kernel:0', 'conv_1_semantic_5/bias:0', 'conv_1_semantic_6/kernel:0', 'conv_1_semantic_6/bias:0'] when minimizing the loss.
WARNING:tensorflow:Gradients do not exist for variables ['conv_0_semantic_upsample_2/kernel:0', 'conv_0_semantic_upsample_2/bias:0', 'conv_0_semantic_upsample_3/kernel:0', 'conv_0_semantic_upsample_3/bias:0', 'conv_0_semantic_upsample_4/kernel:0', 'conv_0_semantic_upsample_4/bias:0', 'conv_0_semantic_upsample_5/kernel:0', 'conv_0_semantic_upsample_5/bias:0', 'conv_0_semantic_upsample_6/kernel:0', 'conv_0_semantic_upsample_6/bias:0', 'conv_0_semantic_2/kernel:0', 'conv_0_semantic_2/bias:0', 'conv_0_semantic_3/kernel:0', 'conv_0_semantic_3/bias:0', 'conv_0_semantic_4/kernel:0', 'conv_0_semantic_4/bias:0', 'conv_0_semantic_5/kernel:0', 'conv_0_semantic_5/bias:0', 'conv_0_semantic_6/kernel:0', 'conv_0_semantic_6/bias:0', 'batch_normalization_0_semantic_2/gamma:0', 'batch_normalization_0_semantic_2/beta:0', 'batch_normalization_0_semantic_3/gamma:0', 'batch_normalization_0_semantic_3/beta:0', 'batch_normalization_0_semantic_4/gamma:0', 'batch_normalization_0_semantic_4/beta:0', 'batch_normalization_0_semantic_5/gamma:0', 'batch_normalization_0_semantic_5/beta:0', 'batch_normalization_0_semantic_6/gamma:0', 'batch_normalization_0_semantic_6/beta:0', 'conv_1_semantic_2/kernel:0', 'conv_1_semantic_2/bias:0', 'conv_1_semantic_3/kernel:0', 'conv_1_semantic_3/bias:0', 'conv_1_semantic_4/kernel:0', 'conv_1_semantic_4/bias:0', 'conv_1_semantic_5/kernel:0', 'conv_1_semantic_5/bias:0', 'conv_1_semantic_6/kernel:0', 'conv_1_semantic_6/bias:0'] when minimizing the loss.
---------------------------------------------------------------------------
UnknownError Traceback (most recent call last)
<ipython-input-86-144b2c018829> in <module>()
30 validation_data=val_data,
31 validation_steps=val_data.y.shape[0] // batch_size,
---> 32 callbacks=train_callbacks)
6 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
58 ctx.ensure_initialized()
59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
62 if name is not None:
UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[node resnet50_retinanetmask/conv1_conv/Conv2D (defined at <ipython-input-86-144b2c018829>:32) ]] [Op:__inference_train_function_125016]
Function call stack:
train_function
Do you have any clues on how to handle this issue?
Best regards,
This issue is migrated from kiosk-redis-consumer
and then from deeepcell-toolbox
.
The retinanet
post-processing functions can OOM, either because of the large response from the models or because of the compute_iou
call in the post-processing.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.