Eric Hu
- Total activity 50
- Last activity
- Member since
- Following 0 users
- Followed by 2 users
- Votes 0
- Subscriptions 20
Comments
Recent activity by Eric Hu Sort by recent activity-
Hi Maxime, This error means that the GPU your notebooks uses is running is out of memory. There are a few ways to possibly resolve this issue: 1. Normally setting the BATCH_SIZE = 16 # ...
-
Hi Aleksey, Thanks for sharing your model. Looks like the slope of the PReLU layer in your model has dimension 3, which is not supported by our internal framework yet. We are planning to add this s...
-
Hi Aleksey, Would you mind sharing your onnx model for us to take a look? We have tested creating dummy models with torch.nn.PReLU(num_parameters=1) and torch.nn.PReLU(num_parameters=num_of_channel...
-
Hi Aleksey, Thanks for your feedback. This is due to current limitation of our internal inference framework. If you intend to broadcast a shared slope across all channels, one alternative is to use...
-
Hi Marco, I've looked into the model you exported from Google AutoML. Looks like it is reading image binaries and converts them to floats via tensorflow::ops::DecodeJpeg inside its graph. Unfortun...
-
Hi Marco, We have investigated the issue you raised and found out that the cause is 'merge_duplicate_nodes' in optimize_graph, commenting out that line resolves the `key not found` issue: Altern...
-
Hi Marco, Thanks for uploading the model. We will take a look and get back to you shortly. Eric
-
Hi Marco, One options is to use one-hot encoding for each letter you are trying to feed. However, unfortunately most text processing related features like LSTM and GRU are not supported for now. Ma...
-
Hi Uniepicgamer, Thank you for your feedback. We are currently looking into your issue. We will be get back to you asap once we resolve this, thanks! Eric
-
Hi Marco, thanks for the feedback! We've updated the Tensorflow guide and changes should be reflected shortly.
