lopuhin / kaggle-dstl Goto Github PK

in train.py
` inputs.append(patch[:, m: -m, m: -m].astype(np.float32))
outputs.append(mask[:, m: -m, m: -m].astype(np.float32))

       if self.hps.needs_dist:
           dist_outputs.append(dist_mask[:, m: -m, m: -m].astype(np.float32))`
   return (torch.from_numpy(np.array(inputs)),
           torch.from_numpy(np.array(outputs)),
           torch.from_numpy(np.array(dist_outputs)))

the return 3th args, (dist_outputs) is null . so it is not transform to torch.
the error message is: RuntimeError: the given numpy array has zero-sized dimensions. Zero-sized dimensions are not supported in PyTorch

in models.py
@property def needs_dist(self): return (self.dist_loss != 0 or self.dist_dice_loss != 0 or self.dist_jaccard_loss != 0)
you can find "title 1" `s if-else decide by this function

however , the source code default this 3 value is 0
in models.py
dist_loss = attr.ib(default=0.0) dist_dice_loss = attr.ib(default=0.0) dist_jaccard_loss = attr.ib(default=0.0)

the web course is : $ ./train.py checkpoint-floder --all --hps dice_loss=10,n_epochs=70
so come up the "title 1" problem.

def log():
    logger.info(
        'Train loss: {loss:.3f}, Jaccard: {jaccard}, '
        'speed: {speed:,} patches/s'.format(
            loss=np.array(losses)[:, -log_step:].mean(),
            speed=int(len(losses[0]) * self.hps.batch_size / (t1 - t00)),
            jaccard=self._format_jaccard(jaccard_stats),
        ))

t0 = t00 = time.time()
log_step = 50
im_log_step = n_batches // log_step * log_step
map_ = (map if no_mp else
        partial(utils.imap_fixed_output_buffer, threads=4))
for i, (x, y, dist_y) in enumerate(map_(gen_batch, range(n_batches))):
    if losses[0] and i % log_step == 0:
        for cls, ls in zip(self.hps.classes, losses):
            self._log_value(
                'loss/cls-{}'.format(cls), np.mean(ls[-log_step:]))
        if self.hps.has_all_classes:
            self._log_value(
                'loss/cls-mean', np.mean([
                    l for ls in losses for l in ls[-log_step:]]))
        pred_y = self.net(self._var(x)).data.cpu()                         
        self._update_jaccard(jaccard_stats, y.numpy(), pred_y.numpy())
        self._log_jaccard(jaccard_stats)
        if i == im_log_step:
            self._log_im(
                x.numpy(), y.numpy(), dist_y.numpy(), pred_y.numpy())
    step_losses = self.train_step(x, y, dist_y)        
                                                        
    for ls, l in zip(losses, step_losses):
        ls.append(l)
    t1 = time.time()
    dt = t1 - t0
    if dt > 10:
        log()
        jaccard_stats = self._jaccard_stats()
        t0 = t1
if losses:
    log()`

Traceback (most recent call last):
  File "./train.py", line 704, in <module>
    main()
  File "./train.py", line 640, in main
    all_im_ids = list(utils.get_wkt_data())
  File "/root/sharedfolder/kaggle-dstl/utils.py", line 41, in get_wkt_data
    with open('./train_wkt_v4.csv') as f:
FileNotFoundError: [Errno 2] No such file or directory: './train_wkt_v4.csv'