search

facebookresearch / ClassyVision

An end-to-end PyTorch framework for image and video classification
https://classyvision.ai
MIT License
1.59k stars 278 forks source link

Could you please provide a config for training efficientnet？ #680

Closed shinianzhihou closed 3 years ago

shinianzhihou commented 3 years ago

Could you please provide a config for training efficientnet？

I am confusing about the config for efficientnet.

shinianzhihou commented 3 years ago

config(model): "model": { "name": "efficientnet_b0", "bn_momentum": 0.01, "bn_epsilon": 1e-3, "drop_connect_rate": 0.0, "num_classes": 15, "width_divisor": 8, "min_width": null, "use_se": true, "heads": [ { "name": "fully_connected", "unique_id": "default_head", "num_classes": 15, "fork_block": "block3-2", "in_plane": 2048 } ] },

Traceback (most recent call last): File "classy_train.py", line 190, in main(args, config) File "classy_train.py", line 112, in main trainer.train(task) File "/home/shinian/ClassyVision/classy_vision/trainer/distributed_trainer.py", line 82, in train super().train(task) File "/home/shinian/ClassyVision/classy_vision/trainer/classy_trainer.py", line 46, in train task.step() File "/home/shinian/ClassyVision/classy_vision/tasks/classy_task.py", line 163, in step self.train_step() File "/home/shinian/ClassyVision/classy_vision/tasks/classification_task.py", line 1017, in train_step output = self.model(sample["input"]) File "/home/shinian/ClassyVision/classy_vision/models/classy_model.py", line 97, in call return self.forward(*args, kwargs) File "/home/shinian/ClassyVision/classy_vision/models/classy_model.py", line 111, in forward out = self.classy_model(*args, *kwargs) File "/opt/conda/envs/rapids/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(input, kwargs) File "/home/shinian/ClassyVision/classy_vision/models/efficientnet.py", line 536, in forward outputs = block(outputs, drop_connect_rate=drop_connect_rate) File "/opt/conda/envs/rapids/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, **kwargs) TypeError: forward() got an unexpected keyword argument 'drop_connect_rate' Traceback (most recent call last): File "/opt/conda/envs/rapids/lib/python3.6/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/opt/conda/envs/rapids/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/opt/conda/envs/rapids/lib/python3.6/site-packages/torch/distributed/launch.py", line 263, in main() File "/opt/conda/envs/rapids/lib/python3.6/site-packages/torch/distributed/launch.py", line 259, in main cmd=cmd)

shinianzhihou commented 3 years ago

where can i find the pretrained model （.pt） for efficientnet?