I am working on a script with data augmentation techniques centercropping,cornercropping and horizontalflip and I want to keep only the centercropping an horizontalflip this is the functions the first one is for the training data
def get_train_utils(opt, model_parameters): assert opt.train_crop in ['random', 'corner', 'center'] spatial_transform = [] #if opt.train_crop == 'random': # spatial_transform.append( # RandomResizedCrop( # opt.sample_size, (opt.train_crop_min_scale, 1.0), #(opt.train_crop_min_ratio, 1.0 / opt.train_crop_min_ratio))) #elif opt.train_crop == 'corner': # scales = [1.0] # scale_step = 1 / (2**(1 / 4)) #for _ in range(1, 5): # scales.append(scales[-1] * scale_step) #spatial_transform.append(MultiScaleCornerCrop(opt.sample_size, scales)) if opt.train_crop == 'center': spatial_transform.append(Resize(opt.sample_size)) spatial_transform.append(CenterCrop(opt.sample_size)) normalize = get_normalize_method(opt.mean, opt.std, opt.no_mean_norm, opt.no_std_norm) if not opt.no_hflip: spatial_transform.append(RandomHorizontalFlip()) if opt.colorjitter: spatial_transform.append(ColorJitter()) spatial_transform.append(ToTensor()) if opt.input_type == 'flow': spatial_transform.append(PickFirstChannels(n=2)) spatial_transform.append(ScaleValue(opt.value_scale)) spatial_transform.append(normalize) spatial_transform = Compose(spatial_transform) assert opt.train_t_crop in ['random', 'center'] temporal_transform = [] if opt.sample_t_stride > 1: temporal_transform.append(TemporalSubsampling(opt.sample_t_stride)) # if opt.train_t_crop == 'random': # temporal_transform.append(TemporalRandomCrop(opt.sample_duration)) if opt.train_t_crop == 'center': temporal_transform.append(TemporalCenterCrop(opt.sample_duration)) temporal_transform = TemporalCompose(temporal_transform) train_data = get_training_data(opt.video_path, opt.annotation_path, opt.dataset, opt.input_type, opt.file_type, spatial_transform, temporal_transform) if opt.distributed: train_sampler = torch.utils.data.distributed.DistributedSampler( train_data) else: train_sampler = None train_loader = torch.utils.data.DataLoader(train_data, batch_size=opt.batch_size, shuffle=(train_sampler is None), num_workers=opt.n_threads, pin_memory=True, sampler=train_sampler, worker_init_fn=worker_init_fn)the second one is for validation data
def get_val_utils(opt): normalize = get_normalize_method(opt.mean, opt.std, opt.no_mean_norm, opt.no_std_norm) spatial_transform = [ Resize(opt.sample_size), CenterCrop(opt.sample_size), ToTensor() ] if opt.input_type == 'flow': spatial_transform.append(PickFirstChannels(n=2)) spatial_transform.extend([ScaleValue(opt.value_scale), normalize]) spatial_transform = Compose(spatial_transform) temporal_transform = [] if opt.sample_t_stride > 1: temporal_transform.append(TemporalSubsampling(opt.sample_t_stride)) temporal_transform.append( TemporalEvenCrop(opt.sample_duration, opt.n_val_samples)) temporal_transform = TemporalCompose(temporal_transform) val_data, collate_fn = get_validation_data(opt.video_path, opt.annotation_path, opt.dataset, opt.input_type, opt.file_type, spatial_transform, temporal_transform) if opt.distributed: val_sampler = torch.utils.data.distributed.DistributedSampler( val_data, shuffle=False) else: val_sampler = None val_loader = torch.utils.data.DataLoader(val_data, batch_size=(opt.batch_size // opt.n_val_samples), shuffle=False, num_workers=opt.n_threads, pin_memory=True, sampler=val_sampler, worker_init_fn=worker_init_fn, collate_fn=collate_fn)and the last one is for inference data
def get_inference_utils(opt): assert opt.inference_crop in ['center', 'nocrop'] normalize = get_normalize_method(opt.mean, opt.std, opt.no_mean_norm, opt.no_std_norm) spatial_transform = [Resize(opt.sample_size)] if opt.inference_crop == 'center': spatial_transform.append(CenterCrop(opt.sample_size)) spatial_transform.append(ToTensor()) if opt.input_type == 'flow': spatial_transform.append(PickFirstChannels(n=2)) spatial_transform.extend([ScaleValue(opt.value_scale), normalize]) spatial_transform = Compose(spatial_transform) temporal_transform = [] if opt.sample_t_stride > 1: temporal_transform.append(TemporalSubsampling(opt.sample_t_stride)) temporal_transform.append( SlidingWindow(opt.sample_duration, opt.inference_stride)) temporal_transform = TemporalCompose(temporal_transform) inference_data, collate_fn = get_inference_data( opt.video_path, opt.annotation_path, opt.dataset, opt.input_type, opt.file_type, opt.inference_subset, spatial_transform, temporal_transform) inference_loader = torch.utils.data.DataLoader( inference_data, batch_size=opt.inference_batch_size, shuffle=False, num_workers=opt.n_threads, pin_memory=True, worker_init_fn=worker_init_fn, collate_fn=collate_fn) return inference_loader, inference_data.class_namesthe functions used are imported from :
from spatial_transforms import (Compose, Normalize, Resize, CenterCrop, CornerCrop, MultiScaleCornerCrop, RandomResizedCrop, RandomHorizontalFlip, ToTensor, ScaleValue, ColorJitter, PickFirstChannels) from temporal_transforms import (LoopPadding, TemporalRandomCrop, TemporalCenterCrop, TemporalEvenCrop, SlidingWindow, TemporalSubsampling) from temporal_transforms import Compose as TemporalComposeI just removed th random an corner cropping from the get_train_util function the line with the # symbole and kept only the center cropping but got this error
runtime error trying to resize storage that is not resizable
the tracebacktraceback_screenshotthe complete code is in this github repository link_to_completecodeI think it's related to the dataloader , it'not able to load the data after I tried to modified it any suggestions what should I do?
2 Related questions 1106 How do I remove/delete a folder that is not empty? 0 What does it mean to assert an object in python? 2 What could be raising this "RuntimeError: Trying to resize storage that is not resizable"? Related questions 1106 How do I remove/delete a folder that is not empty? 0 What does it mean to assert an object in python? 2 What could be raising this "RuntimeError: Trying to resize storage that is not resizable"? 774 Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2 90 CUDA runtime error (59) : device-side assert triggered 1 Center widgets in Kivy 454 Error "filename.whl is not a supported wheel on this platform" Load 4 more related questions Show fewer related questions Reset to default
