Abhishek Kumar Annamraju

Hi, you can use Visualize_With_Netron function to get a visual view of the network layers. Will soon add model summary function.

Thank you for pointing out the issue. We will try to resolve it as soon as possible. On your end please check by downgrading pytorch to version 1.4

Did a version downgrade help your case?

We are unable to reproduce that error with pytorch v1.4. Please check and let us know

the error is because onnx is still incompatible with torch 1.6; Hence reducing torch to 1.4 and torchvision 0.5 will resolve the errors. Requirement files have been updated accordingly.

> When I use torch 1.4 and torchvision 0.5, I am getting > ## loading annotations into memory... > Done (t=0.13s) > creating index... > index created! > > RuntimeError...

WAY 1: a) Switch to torch==1.4, torchvision==0.5 and efficientnet_pytorch==0.6.3 b) Train your first detector c) Then resume or reload training from this checkpoint. WAY 2: When you clone the library...

Please share your code.

The image size is 32? For EfficientNet - b0 image size should be 512. See this example - https://github.com/Tessellate-Imaging/Monk_Object_Detection/blob/master/example_notebooks/4_efficientdet/train%20-%20with%20validation%20dataset.ipynb

If the image shapes were inconsistent it auto switched to default shapes. Since latest efficientnet_pytorch upgrade requires a manual input of shapes we have made the argument as a required...