NVIDIA-AI-IOT / jetracer

An autonomous AI racecar using NVIDIA Jetson Nano
MIT License
1.07k stars 321 forks source link

Training Error #152

Open wilson030402 opened 3 months ago

wilson030402 commented 3 months ago

Hello team,

I am currently trying to train the Resnet-18 model with the interactive regression notebook with a dataset of 1400 images, when I launch a training I get the following error:

AttributeError Traceback (most recent call last)

in train_eval(is_training) 35 error_count = 0.0 ---> 36 for images, category_idx, xy in iter(train_loader): 37 # send data to device /usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py in __next__(self) 362 def __next__(self): --> 363 data = self._next_data() 364 self._num_yielded += 1 /usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py in _next_data(self) 402 index = self._next_index() # may raise StopIteration --> 403 data = self._dataset_fetcher.fetch(index) # may raise StopIteration 404 if self._pin_memory: /usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py in fetch(self, possibly_batched_index) 43 if self.auto_collation: ---> 44 data = [self.dataset[idx] for idx in possibly_batched_index] 45 else: /usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py in (.0) 43 if self.auto_collation: ---> 44 data = [self.dataset[idx] for idx in possibly_batched_index] 45 else: ~/jetracer/notebooks/xy_dataset.py in __getitem__(self, idx) 26 image = cv2.imread(ann['image_path'], cv2.IMREAD_COLOR) ---> 27 image = PIL.Image.fromarray(image) 28 width = image.width /usr/lib/python3/dist-packages/PIL/Image.py in fromarray(obj, mode) 2420 """ -> 2421 arr = obj.__array_interface__ 2422 shape = arr['shape'] AttributeError: 'NoneType' object has no attribute '__array_interface__' During handling of the above exception, another exception occurred: NameError Traceback (most recent call last) in (c) 78 state_widget.value = 'live' 79 ---> 80 train_button.on_click(lambda c: train_eval(is_training=True)) 81 eval_button.on_click(lambda c: train_eval(is_training=False)) 82 in train_eval(is_training) 70 else: 71 break ---> 72 except e: 73 pass 74 model = model.eval() NameError: name 'e' is not defined Has anyone had this error before or can anyone help me, please ? Thanks, Wilson