EfficientDet Pytorch-lightning with EfficientNet v2 backbone Blog Post.ipynb

EfficientDet Pytorch-lightning with EfficientNet v2 backbone Blog Post.ipynb

hi,
I got this error :

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Input In [41], in <cell line: 4>()
      1 from pytorch_lightning import Trainer
      2 trainer = Trainer(gpus=[0], max_epochs=5, num_sanity_val_steps=1)
----> 4 trainer.fit(model, dm)

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\trainer\trainer.py:553, in Trainer.fit(self, model, train_dataloaders, val_dataloaders, datamodule, train_dataloader)
    547 self.data_connector.attach_data(
    548     model, train_dataloaders=train_dataloaders, val_dataloaders=val_dataloaders, datamodule=datamodule
    549 )
    551 self.checkpoint_connector.resume_start()
--> 553 self._run(model)
    555 assert self.state.stopped
    556 self.training = False

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\trainer\trainer.py:918, in Trainer._run(self, model)
    915 self.checkpoint_connector.restore_training_state()
    917 # dispatch `start_training` or `start_evaluating` or `start_predicting`
--> 918 self._dispatch()
    920 # plugin will finalized fitting (e.g. ddp_spawn will load trained model)
    921 self._post_dispatch()

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\trainer\trainer.py:986, in Trainer._dispatch(self)
    984     self.accelerator.start_predicting(self)
    985 else:
--> 986     self.accelerator.start_training(self)

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\accelerators\accelerator.py:92, in Accelerator.start_training(self, trainer)
     91 def start_training(self, trainer: "pl.Trainer") -> None:
---> 92     self.training_type_plugin.start_training(trainer)

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\plugins\training_type\training_type_plugin.py:161, in TrainingTypePlugin.start_training(self, trainer)
    159 def start_training(self, trainer: "pl.Trainer") -> None:
    160     # double dispatch to initiate the training loop
--> 161     self._results = trainer.run_stage()

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\trainer\trainer.py:996, in Trainer.run_stage(self)
    994 if self.predicting:
    995     return self._run_predict()
--> 996 return self._run_train()

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\trainer\trainer.py:1031, in Trainer._run_train(self)
   1028 if not self.is_global_zero and self.progress_bar_callback is not None:
   1029     self.progress_bar_callback.disable()
-> 1031 self._run_sanity_check(self.lightning_module)
   1033 # enable train mode
   1034 self.model.train()

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\trainer\trainer.py:1115, in Trainer._run_sanity_check(self, ref_model)
   1113 # run eval step
   1114 with torch.no_grad():
-> 1115     self._evaluation_loop.run()
   1117 self.on_sanity_check_end()
   1119 # reset validation metrics

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\loops\base.py:111, in Loop.run(self, *args, **kwargs)
    109 try:
    110     self.on_advance_start(*args, **kwargs)
--> 111     self.advance(*args, **kwargs)
    112     self.on_advance_end()
    113     self.iteration_count += 1

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\loops\dataloader\evaluation_loop.py:110, in EvaluationLoop.advance(self, *args, **kwargs)
    107 dataloader_iter = enumerate(dataloader)
    108 dl_max_batches = self._max_batches[self.current_dataloader_idx]
--> 110 dl_outputs = self.epoch_loop.run(
    111     dataloader_iter, self.current_dataloader_idx, dl_max_batches, self.num_dataloaders
    112 )
    114 # store batch level output per dataloader
    115 if self.should_track_batch_outputs_for_epoch_end:

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\loops\base.py:111, in Loop.run(self, *args, **kwargs)
    109 try:
    110     self.on_advance_start(*args, **kwargs)
--> 111     self.advance(*args, **kwargs)
    112     self.on_advance_end()
    113     self.iteration_count += 1

File ~\Anaconda3\envs\SiT\lib\site-packages\pytorch_lightning\loops\epoch\evaluation_epoch_loop.py:93, in EvaluationEpochLoop.advance(self, dataloader_iter, dataloader_idx, dl_max_batches, num_dataloaders)
     80 """Calls the evaluation step with the corresponding hooks and updates the logger connector.
     81 
     82 Args:
   (...)
     89     StopIteration: If the current batch is None
     90 """
     91 void(dl_max_batches, num_dataloaders)
---> 93 batch_idx, batch = next(dataloader_iter)
     95 if batch is None:
     96     raise StopIteration

File ~\Anaconda3\envs\SiT\lib\site-packages\torch\utils\data\dataloader.py:521, in _BaseDataLoaderIter.__next__(self)
    519 if self._sampler_iter is None:
    520     self._reset()
--> 521 data = self._next_data()
    522 self._num_yielded += 1
    523 if self._dataset_kind == _DatasetKind.Iterable and \
    524         self._IterableDataset_len_called is not None and \
    525         self._num_yielded > self._IterableDataset_len_called:

File ~\Anaconda3\envs\SiT\lib\site-packages\torch\utils\data\dataloader.py:561, in _SingleProcessDataLoaderIter._next_data(self)
    559 def _next_data(self):
    560     index = self._next_index()  # may raise StopIteration
--> 561     data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
    562     if self._pin_memory:
    563         data = _utils.pin_memory.pin_memory(data)

File ~\Anaconda3\envs\SiT\lib\site-packages\torch\utils\data\_utils\fetch.py:49, in _MapDatasetFetcher.fetch(self, possibly_batched_index)
     47 def fetch(self, possibly_batched_index):
     48     if self.auto_collation:
---> 49         data = [self.dataset[idx] for idx in possibly_batched_index]
     50     else:
     51         data = self.dataset[possibly_batched_index]

File ~\Anaconda3\envs\SiT\lib\site-packages\torch\utils\data\_utils\fetch.py:49, in <listcomp>(.0)
     47 def fetch(self, possibly_batched_index):
     48     if self.auto_collation:
---> 49         data = [self.dataset[idx] for idx in possibly_batched_index]
     50     else:
     51         data = self.dataset[possibly_batched_index]

Input In [36], in EfficientDetDataset.__getitem__(self, index)
     43 (
     44     image,
     45     pascal_bboxes,
     46     class_labels,
     47     image_id,
     48 ) = self.ds.get_image_and_labels_by_idx(index)
     50 sample = {
     51     "image": np.array(image, dtype=np.float32),
     52     "bboxes": pascal_bboxes,
     53     "labels": class_labels,
     54 }
---> 56 sample = self.transforms(**sample)
     57 sample["bboxes"] = np.array(sample["bboxes"])
     58 image = sample["image"]

File ~\Anaconda3\envs\SiT\lib\site-packages\albumentations\core\composition.py:182, in Compose.__call__(self, force_apply, *args, **data)
    179     for p in self.processors.values():
    180         p.preprocess(data)
--> 182 data = t(force_apply=force_apply, **data)
    184 if dual_start_end is not None and idx == dual_start_end[1]:
    185     for p in self.processors.values():

File ~\Anaconda3\envs\SiT\lib\site-packages\albumentations\core\transforms_interface.py:90, in BasicTransform.__call__(self, force_apply, *args, **kwargs)
     85             warn(
     86                 self.get_class_fullname() + " could work incorrectly in ReplayMode for other input data"
     87                 " because its' params depend on targets."
     88             )
     89         kwargs[self.save_key][id(self)] = deepcopy(params)
---> 90     return self.apply_with_params(params, **kwargs)
     92 return kwargs

File ~\Anaconda3\envs\SiT\lib\site-packages\albumentations\core\transforms_interface.py:103, in BasicTransform.apply_with_params(self, params, force_apply, **kwargs)
    101     target_function = self._get_target_function(key)
    102     target_dependencies = {k: kwargs[k] for k in self.target_dependence.get(key, [])}
--> 103     res[key] = target_function(arg, **dict(params, **target_dependencies))
    104 else:
    105     res[key] = None

File ~\Anaconda3\envs\SiT\lib\site-packages\albumentations\augmentations\transforms.py:602, in Normalize.apply(self, image, **params)
    601 def apply(self, image, **params):
--> 602     return F.normalize(image, self.mean, self.std, self.max_pixel_value)

File ~\Anaconda3\envs\SiT\lib\site-packages\albumentations\augmentations\functional.py:141, in normalize(img, mean, std, max_pixel_value)
    138 denominator = np.reciprocal(std, dtype=np.float32)
    140 img = img.astype(np.float32)
--> 141 img -= mean
    142 img *= denominator
    143 return img

ValueError: operands could not be broadcast together with shapes (512,512) (3,) (512,512) 

any idea to solve this?

Hi @Chris-hughes10. thank you for this great job.
I'm new in this field. I have a dataset that is in Pascal VOC format with XML annotations. How can I use it to training? Can you please help me?

Dear @Chris-hughes10, Thank you for this amazing work.

Have you done any work as to convert the saved model from torch.save() to onnx?

I am asking this question because I got stuck trying to convert the saved model. The conversion script that I am using is this:

import os
import io
import numpy as np
import pandas as pd
from functools import partial

from custom_utils import widerface_data_adaptor
from custom_utils import effdet_data_module
from custom_utils import effdet_model

import torch
import torch.onnx

from effdet import get_efficientdet_config, EfficientDet, DetBenchPredict

model_checkpoint_path = "/home/soroush.tabadkani/projects/efficientdet-pytorch/checkpoints/trained_effdet.pt"
device = torch.device('cuda')

input_shape = (1, 3, 512, 512)
dummy_input = torch.randn(input_shape, dtype=torch.float32, requires_grad=True).to(device)

net = effdet_model.EfficientDetModel(
    num_classes=1,
    img_size=512
    )

net.load_state_dict(torch.load(model_checkpoint_path))
net.eval()

dynamic_axes = {out:{0:'batch_size'} for out in ['outputs']}
dynamic_axes.update({input: {0: 'batch_size'} for input in ['inputs']})
              
torch.onnx.export(net.cuda(),
                  (dummy_input),
                  'efficientdet-d0.onnx',
                  input_names = ['inputs'],
                  output_names = ['outputs'],
                  verbose=True,
                  dynamic_axes=dynamic_axes,
                  opset_version=12)

and the error I get is:

torch.onnx.export(net.cuda(),
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/onnx/__init__.py", line 271, in export
    return utils.export(model, args, f, export_params, verbose, training,
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/onnx/utils.py", line 88, in export
    _export(model, args, f, export_params, verbose, training, input_names, output_names,
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/onnx/utils.py", line 694, in _export
    _model_to_graph(model, args, verbose, input_names,
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/onnx/utils.py", line 457, in _model_to_graph
    graph, params, torch_out, module = _create_jit_graph(model, args,
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/onnx/utils.py", line 420, in _create_jit_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args)
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/onnx/utils.py", line 380, in _trace_and_get_graph_from_model
    torch.jit._get_trace_graph(model, args, strict=False, _force_outplace=False, _return_inputs_states=True)
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/jit/_trace.py", line 1139, in _get_trace_graph
    outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/nn/modules/module.py", line 891, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/jit/_trace.py", line 125, in forward
    graph, out = torch._C._create_graph_by_tracing(
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/jit/_trace.py", line 116, in wrapper
    outs.append(self.inner(*trace_inputs))
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self._slow_forward(*input, **kwargs)
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/torch/nn/modules/module.py", line 862, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/home/soroush.tabadkani/projects/efficientdet-pytorch/env_test/lib/python3.8/site-packages/pytorch_lightning/core/decorators.py", line 62, in auto_transfer_args
    return fn(self, *args, **kwargs)
TypeError: forward() missing 1 required positional argument: 'targets'

No matter how many approaches I tried to solve this problem with, they all eventually resulted in the error above. Any help or guidance if you can kindly provide me with is deeply appreciated.

Hi @ramdhan1989 Were you able to solve the operands broadcast issue? I am facing a similar error when training the model

@Chris-hughes10
My model is predicting

The model i have trained has 15 classes. What could have possibly gone wrong?