EfficientNet-PyTorch

EfficientNet-PyTorch copied to clipboard

Cant wait to see the new model!

LovelyQuantum

Unable to load ONNX model into TensorRT

3

pytorch : 1.4.0a0 + 46f32e1 onnx : 1.6.0 onnx2trt: 7.0 tensorrt: 7.0.0.11   Any suggestions on this issue? Thanks

kaishian

allow to load pretrained weights when the include_top variable is False

1

This merge request is related to the bug #278 The class initialization is failed when called using `from_pretrained(.., include_top=False)` function or when the number of classes is not equal to...

kurnianggoro

Update utils.py

1

sathyapriyaa-sketch

Hi all, I want to add a new head for a simple two classes classification task, I will have 2 , 6 classes to classify. How do I add a...

www7890

How to compute the params?

1

Hi! luke. We are curious about how to calculate the parameter size. When we calculate the parameter size through **thop**, it is far from what is listed in your Readme...

linlll

How to change BN to GN and FRN layer in efficientnet?

1

i was trying groupnormalization for efficientnet , my model code is : ``` out_dim = 5 enet_type = 'efficientnet-b0' pretrained_model = { 'efficientnet-b0': '../input/efficientnet-pytorch/efficientnet-b0-08094119.pth' } class enetv2(nn.Module): def __init__(self, backbone,...

mobassir94

Hello, I'm using efficientnet well. When I use this model, the purpose is to extract the activation layer value of the feature extractor part (. In other words, can the...

ingbeeedd

You have probably done this already, but wanted to try just for fun. I am a beginner, so would love some feedback!

vegardstenberg

Consider if user has GPU/CPU while calling `torch.load()`

3

https://github.com/lukemelas/EfficientNet-PyTorch/blob/7e8b0d312162f335785fb5dcfa1df29a75a1783a/efficientnet_pytorch/utils.py#L598 ```python if torch.cuda.is_available(): device = torch.device("cuda") else: device = torch.device("cpu") state_dict = torch.load(weights_path, map_location=device) ```

BRO3886