search

YehLi / xmodaler

X-modaler is a versatile and high-performance codebase for cross-modal analytics(e.g., image captioning, video captioning, vision-language pre-training, visual question answering, visual commonsense reasoning, and cross-modal retrieval).
Other
1.03k stars 111 forks source link

No such file or directory: '../open_source_dataset/mscoco_dataset/features/up_down\\313724.npz' #22

Closed monkeycc closed 3 years ago

monkeycc commented 3 years ago 
python train_net.py --num-gpus 1 --config-file configs/image_caption/updown/updown.yaml

SCORER:
  CIDER_CACHED: ../open_source_dataset/mscoco_dataset/mscoco_train_cider.pkl
  EOS_ID: 0
  GT_PATH: ../open_source_dataset/mscoco_dataset/mscoco_train_gts.pkl
  NAME: BaseScorer
  TYPES: ['Cider']
  WEIGHTS: [1.0]
SEED: -1
SOLVER:
  ALPHA: 0.99
  AMSGRAD: False
  BASE_LR: 0.0005
  BETAS: [0.9, 0.999]
  BIAS_LR_FACTOR: 1.0
  CENTERED: False
  CHECKPOINT_PERIOD: 1
  DAMPENING: 0.0
  EPOCH: 30
  EPS: 1e-08
  EVAL_PERIOD: 1
  GRAD_CLIP: 0.1
  GRAD_CLIP_TYPE: value
  INITIAL_ACCUMULATOR_VALUE: 0.0
  LR_DECAY: 0.0
  MOMENTUM: 0.9
  NAME: Adam
  NESTEROV: 0.0
  NORM_TYPE: 2.0
  WEIGHT_DECAY: 0.0
  WEIGHT_DECAY_BIAS: 0.0
  WEIGHT_DECAY_NORM: 0.0
  WRITE_PERIOD: 20
VERSION: 1
[09/27 19:21:02 xmodaler]: Full config saved to ./output\config.yaml
[09/27 19:21:02 xl.utils.env]: Using a generated random seed 2862719
[09/27 19:21:04 xl.engine.defaults]: Model:
RnnAttEncoderDecoder(
  (token_embed): TokenBaseEmbedding(
    (embeddings): Embedding(10200, 1024)
    (embeddings_act): ReLU()
    (embeddings_dropout): Dropout(p=0.5, inplace=False)
  )
  (visual_embed): VisualBaseEmbedding(
    (embeddings): Linear(in_features=2048, out_features=1024, bias=True)
    (embeddings_act): ReLU()
    (embeddings_dropout): Dropout(p=0.5, inplace=False)
  )
  (encoder): UpDownEncoder()
  (decoder): UpDownDecoder(
    (lstm1): LSTMCell(3072, 1024)
    (lstm2): LSTMCell(2048, 1024)
    (att): BaseAttention(
      (w_h): Linear(in_features=1024, out_features=512, bias=False)
      (act): Tanh()
      (w_alpha): Linear(in_features=512, out_features=1, bias=False)
      (softmax): Softmax(dim=-1)
    )
    (p_att_feats): Linear(in_features=1024, out_features=512, bias=True)
  )
  (predictor): BasePredictor(
    (logits): Linear(in_features=1024, out_features=10200, bias=True)
    (dropout): Dropout(p=0.5, inplace=False)
  )
  (greedy_decoder): GreedyDecoder()
  (beam_searcher): BeamSearcher()
)
[09/27 19:21:05 xl.datasets.common]: Serializing 113287 elements to byte tensors and concatenating them all ...
[09/27 19:21:06 xl.datasets.common]: Serialized dataset takes 115.74 MiB
[09/27 19:21:06 xl.datasets.common]: Serializing 5000 elements to byte tensors and concatenating them all ...
[09/27 19:21:06 xl.datasets.common]: Serialized dataset takes 0.17 MiB
[09/27 19:21:06 xl.datasets.common]: Serializing 5000 elements to byte tensors and concatenating them all ...
[09/27 19:21:06 xl.datasets.common]: Serialized dataset takes 0.17 MiB
loading annotations into memory...
Done (t=0.06s)
creating index...
index created!
loading annotations into memory...
Done (t=0.07s)
creating index...
index created!
[09/27 19:21:16 fvcore.common.checkpoint]: No checkpoint found. Initializing model from scratch
[09/27 19:21:16 xl.engine.train_loop]: Starting training from iteration 0
ERROR [09/27 19:21:16 xl.engine.train_loop]: Exception during training:
Traceback (most recent call last):
  File "D:\xmodaler\xmodaler\engine\train_loop.py", line 151, in train
    self.run_step()
  File "D:\xmodaler\xmodaler\engine\defaults.py", line 496, in run_step
    data = next(self._train_data_loader_iter)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 517, in __next__
    data = self._next_data()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1225, in _process_data
    data.reraise()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\_utils.py", line 429, in reraise
    raise self.exc_type(msg)
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "D:\xmodaler\xmodaler\datasets\common.py", line 42, in __getitem__
    data = self._map_func(self._dataset[cur_idx])
  File "D:\xmodaler\xmodaler\datasets\images\mscoco.py", line 103, in __call__
    content = read_np(feat_path)
  File "D:\xmodaler\xmodaler\functional\func_io.py", line 22, in read_np
    content = np.load(path)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\numpy\lib\npyio.py", line 416, in load
    fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '../open_source_dataset/mscoco_dataset/features/up_down\\369199.npz'

[09/27 19:21:16 xl.engine.hooks]: Total training time: 0:00:00 (0:00:00 on hooks)
[09/27 19:21:16 xl.utils.events]:  iter: 0    lr: N/A  max_mem: 204M
Traceback (most recent call last):
  File "train_net.py", line 68, in <module>
    args=(args,),
  File "D:\xmodaler\xmodaler\engine\launch.py", line 86, in launch
    main_func(*args)
  File "train_net.py", line 56, in main
    return trainer.train()
  File "D:\xmodaler\xmodaler\engine\defaults.py", line 365, in train
    super().train(self.start_iter, self.max_iter)
  File "D:\xmodaler\xmodaler\engine\train_loop.py", line 151, in train
    self.run_step()
  File "D:\xmodaler\xmodaler\engine\defaults.py", line 496, in run_step
    data = next(self._train_data_loader_iter)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 517, in __next__
    data = self._next_data()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1225, in _process_data
    data.reraise()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\_utils.py", line 429, in reraise
    raise self.exc_type(msg)
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "D:\xmodaler\xmodaler\datasets\common.py", line 42, in __getitem__
    data = self._map_func(self._dataset[cur_idx])
  File "D:\xmodaler\xmodaler\datasets\images\mscoco.py", line 103, in __call__
    content = read_np(feat_path)
  File "D:\xmodaler\xmodaler\functional\func_io.py", line 22, in read_np
    content = np.load(path)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\numpy\lib\npyio.py", line 416, in load
    fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '../open_source_dataset/mscoco_dataset/features/up_down\\369199.npz'
jianjieluo commented 3 years ago

Hi @monkeycc ,

You need to setup the corresponding datasets following datasets before training UPDOWN model.

For MSCOCO dataset, please down the bottom up features from https://github.com/peteanderson80/bottom-up-attention and convert them into npz format with tools/create_feats.py.

Best, Jianjie

1301358882 commented 10 months ago 
python train_net.py --num-gpus 1 --config-file configs/image_caption/updown/updown.yaml

SCORER:
  CIDER_CACHED: ../open_source_dataset/mscoco_dataset/mscoco_train_cider.pkl
  EOS_ID: 0
  GT_PATH: ../open_source_dataset/mscoco_dataset/mscoco_train_gts.pkl
  NAME: BaseScorer
  TYPES: ['Cider']
  WEIGHTS: [1.0]
SEED: -1
SOLVER:
  ALPHA: 0.99
  AMSGRAD: False
  BASE_LR: 0.0005
  BETAS: [0.9, 0.999]
  BIAS_LR_FACTOR: 1.0
  CENTERED: False
  CHECKPOINT_PERIOD: 1
  DAMPENING: 0.0
  EPOCH: 30
  EPS: 1e-08
  EVAL_PERIOD: 1
  GRAD_CLIP: 0.1
  GRAD_CLIP_TYPE: value
  INITIAL_ACCUMULATOR_VALUE: 0.0
  LR_DECAY: 0.0
  MOMENTUM: 0.9
  NAME: Adam
  NESTEROV: 0.0
  NORM_TYPE: 2.0
  WEIGHT_DECAY: 0.0
  WEIGHT_DECAY_BIAS: 0.0
  WEIGHT_DECAY_NORM: 0.0
  WRITE_PERIOD: 20
VERSION: 1
[09/27 19:21:02 xmodaler]: Full config saved to ./output\config.yaml
[09/27 19:21:02 xl.utils.env]: Using a generated random seed 2862719
[09/27 19:21:04 xl.engine.defaults]: Model:
RnnAttEncoderDecoder(
  (token_embed): TokenBaseEmbedding(
    (embeddings): Embedding(10200, 1024)
    (embeddings_act): ReLU()
    (embeddings_dropout): Dropout(p=0.5, inplace=False)
  )
  (visual_embed): VisualBaseEmbedding(
    (embeddings): Linear(in_features=2048, out_features=1024, bias=True)
    (embeddings_act): ReLU()
    (embeddings_dropout): Dropout(p=0.5, inplace=False)
  )
  (encoder): UpDownEncoder()
  (decoder): UpDownDecoder(
    (lstm1): LSTMCell(3072, 1024)
    (lstm2): LSTMCell(2048, 1024)
    (att): BaseAttention(
      (w_h): Linear(in_features=1024, out_features=512, bias=False)
      (act): Tanh()
      (w_alpha): Linear(in_features=512, out_features=1, bias=False)
      (softmax): Softmax(dim=-1)
    )
    (p_att_feats): Linear(in_features=1024, out_features=512, bias=True)
  )
  (predictor): BasePredictor(
    (logits): Linear(in_features=1024, out_features=10200, bias=True)
    (dropout): Dropout(p=0.5, inplace=False)
  )
  (greedy_decoder): GreedyDecoder()
  (beam_searcher): BeamSearcher()
)
[09/27 19:21:05 xl.datasets.common]: Serializing 113287 elements to byte tensors and concatenating them all ...
[09/27 19:21:06 xl.datasets.common]: Serialized dataset takes 115.74 MiB
[09/27 19:21:06 xl.datasets.common]: Serializing 5000 elements to byte tensors and concatenating them all ...
[09/27 19:21:06 xl.datasets.common]: Serialized dataset takes 0.17 MiB
[09/27 19:21:06 xl.datasets.common]: Serializing 5000 elements to byte tensors and concatenating them all ...
[09/27 19:21:06 xl.datasets.common]: Serialized dataset takes 0.17 MiB
loading annotations into memory...
Done (t=0.06s)
creating index...
index created!
loading annotations into memory...
Done (t=0.07s)
creating index...
index created!
[09/27 19:21:16 fvcore.common.checkpoint]: No checkpoint found. Initializing model from scratch
[09/27 19:21:16 xl.engine.train_loop]: Starting training from iteration 0
ERROR [09/27 19:21:16 xl.engine.train_loop]: Exception during training:
Traceback (most recent call last):
  File "D:\xmodaler\xmodaler\engine\train_loop.py", line 151, in train
    self.run_step()
  File "D:\xmodaler\xmodaler\engine\defaults.py", line 496, in run_step
    data = next(self._train_data_loader_iter)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 517, in __next__
    data = self._next_data()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1225, in _process_data
    data.reraise()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\_utils.py", line 429, in reraise
    raise self.exc_type(msg)
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "D:\xmodaler\xmodaler\datasets\common.py", line 42, in __getitem__
    data = self._map_func(self._dataset[cur_idx])
  File "D:\xmodaler\xmodaler\datasets\images\mscoco.py", line 103, in __call__
    content = read_np(feat_path)
  File "D:\xmodaler\xmodaler\functional\func_io.py", line 22, in read_np
    content = np.load(path)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\numpy\lib\npyio.py", line 416, in load
    fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '../open_source_dataset/mscoco_dataset/features/up_down\\369199.npz'

[09/27 19:21:16 xl.engine.hooks]: Total training time: 0:00:00 (0:00:00 on hooks)
[09/27 19:21:16 xl.utils.events]:  iter: 0    lr: N/A  max_mem: 204M
Traceback (most recent call last):
  File "train_net.py", line 68, in <module>
    args=(args,),
  File "D:\xmodaler\xmodaler\engine\launch.py", line 86, in launch
    main_func(*args)
  File "train_net.py", line 56, in main
    return trainer.train()
  File "D:\xmodaler\xmodaler\engine\defaults.py", line 365, in train
    super().train(self.start_iter, self.max_iter)
  File "D:\xmodaler\xmodaler\engine\train_loop.py", line 151, in train
    self.run_step()
  File "D:\xmodaler\xmodaler\engine\defaults.py", line 496, in run_step
    data = next(self._train_data_loader_iter)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 517, in __next__
    data = self._next_data()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\dataloader.py", line 1225, in _process_data
    data.reraise()
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\_utils.py", line 429, in reraise
    raise self.exc_type(msg)
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "D:\xmodaler\xmodaler\datasets\common.py", line 42, in __getitem__
    data = self._map_func(self._dataset[cur_idx])
  File "D:\xmodaler\xmodaler\datasets\images\mscoco.py", line 103, in __call__
    content = read_np(feat_path)
  File "D:\xmodaler\xmodaler\functional\func_io.py", line 22, in read_np
    content = np.load(path)
  File "C:\ProgramData\Anaconda3\envs\xmodaler\lib\site-packages\numpy\lib\npyio.py", line 416, in load
    fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: '../open_source_dataset/mscoco_dataset/features/up_down\\369199.npz'

Hello, may i ask that have you solved your problem? I had the same problem. Could you ask me how to solve it?