sushreebarsa
sushreebarsa
@ThorvaldAagaard Please ensure that your environment and TensorFlow version are fully optimized for your new hardware. Also kindly check if TensorFlow is correctly utilizing all available cores and try with...
@ThorvaldAagaard Thank you for the update! TF v1.x is not actively supported and for migration please check [this](https://www.tensorflow.org/guide/migrate) reference. It is highly recommended to use the latest. If you still...
@ThorvaldAagaard Could you ensure that data loading and preprocessing are not bottlenecks. You could use multi-threaded data loading and preprocessing with tf.data.Dataset. Please use Prefetch and parallelize the data pipeline...
@weebao I tried to modify the code , could you please have a look at the gist [here](https://colab.research.google.com/gist/sushreebarsa/2cc350a77f8a705082d80805c8e81cd5/70267.ipynb) and let us know if it helps? Thank you!
@weebao On your local machine please check the following; ``` import tensorflow as tf print(tf.__version__) ``` If the version doesn't match then you can install the same version manually; ```...
@cpappasILMX This typically happens if the build system mistakenly uses macOS-specific settings. To resolve this issue, kindly follow these steps: ``` export ANDROID_NDK_HOME=/path/to/your/android-ndk export ANDROID_SDK_HOME=/path/to/your/android-sdk export PATH=$ANDROID_NDK_HOME:$ANDROID_SDK_HOME/tools:$PATH build --config=android build...
@jvishnuvardhan Was able to replicate the issue on colab using TF v[2.7.0 ](https://colab.research.google.com/gist/sushreebarsa/1efe3f7c4d2ac791d20785f5bf532856/model_save_fails_conv2dtranspose_qat_tf2-7-0.ipynb#scrollTo=ZWW2oEw3CoNF)and [2.8.0](https://colab.research.google.com/gist/sushreebarsa/305b03444505a9a715a9233568008a0c/model_save_fails_conv2dtranspose_qat_tf2-8-0.ipynb#scrollTo=SSMv-TQBEseY) ,please find the attached gists .Thanks!
@JossWhittle I tried to replicate the issue on colab ,could you please find this [gist](https://colab.research.google.com/gist/sushreebarsa/af56a395e31b9e8e42ca9b06f7a5c5eb/55889.ipynb) and confirm the same? Thanks!
@JossWhittle Thank you for the update! @chunduriv I was able to reproduce the issue on colab , please find the gist [here](https://colab.research.google.com/gist/sushreebarsa/134aeb32e8eb89789e694b3d836908ab/55889.ipynb).Thank you!
@binbinxue Sorry for the late response! Could you try to reshape it to occupy an extra dimension, run the deconvolution, and then reshape it back. Please refer to this [doc](https://keras.io/api/layers/convolution_layers/convolution1d/)...