-
Hi! Thank you guys for the better, cleaner new Keras! The promise of backend-agnostic models is just fantastic.
Problem is, the new framework seems to have lost some capabilities of its predecess…
-
It's a very nieche problem, but tripped me over big time :')
### Issue
For `model.eval()` , `z_pred` will not have tracked gradients (`z_pred.requires_gradient==False`).
For custom torch.autog…
-
**Is your feature request related to a problem? Please describe.**
No
I think an essential usecase is to be able to fine tune a model. Currently the code can load a model then continue training all …
-
using "tf2onnx.convert.from_function" on lambda with Keras model,
tf2onnx 1.13 - works ok, batch normalization layer has members "mean" and "var"
tf2onnx 1.14 - batch normalization layer has membe…
-
Hey, I tried porting your repository to a keras version , but for some reason, when I train, the validation loss is always 0.2 which is alpha for me, but training loss keeps on changing. My base netw…
-
I have the following setup.
- Lambda handler:
```go
package main
import (
"context"
"github.com/aws/aws-lambda-go/events"
"github.com/aws/aws-lambda-go/lambda"
"github.com/awslabs/aw…
-
### Bug description
I've been following the serverless and lambda enhancements and performance improvements for quite some time that you all have made but I still seem to notice that my lambda even w…
imoby updated
2 weeks ago
-
Great library I'm just wondering if anyone has managed to deploy this as an AWS lambda function (with or without a lambda layer). It seems the `puppeteer` module is quite large which makes things a bi…
-
Does anyone know how to view the model's architecture diagram? Whether it's using TensorBoard or attempting to convert to ONNX format, I'm encountering errors.Traceback (most recent call last):
Fil…
-
When I run the joint model, I hava the error :ValueError: Operands could not be broadcast together with shapes (64, 64, 2) (64, 64, 5). Can you help me to slove this?