def __init__(self, batch_size, num_threads, device_id, prefetch, seed): super(CommonPipeline, self).__init__(batch_size, num_threads, device_id, prefetch_queue_depth=prefetch) self.decode_cpu = ops.HostDecoder(device="cpu", output_type=types.RGB) self.decode_crop = ops.HostDecoderSlice(device="cpu", output_type=types.RGB) self.crop = ops.SSDRandomCrop(device="cpu", num_attempts=1, seed=seed) self.crop2 = ops.RandomBBoxCrop( device="cpu", aspect_ratio=[0.5, 2.0], thresholds=[0, 0.1, 0.3, 0.5, 0.7, 0.9], scaling=[0.3, 1.0], ltrb=True, seed=seed) self.slice_cpu = ops.Slice(device="cpu") self.slice_gpu = ops.Slice(device="gpu") self.flip_cpu = ops.Flip(device="cpu") self.bb_flip_cpu = ops.BbFlip(device="cpu", ltrb=True) self.flip_gpu = ops.Flip(device="gpu") self.bb_flip_gpu = ops.BbFlip(device="gpu", ltrb=True)
def __init__(self, batch_size, device_id, file_root, annotations_file, num_gpus, output_fp16=False, output_nhwc=False, pad_output=False, num_threads=1, seed=15): super(COCOPipeline, self).__init__(batch_size=batch_size, device_id=device_id, num_threads=num_threads, seed=seed) if torch.distributed.is_initialized(): shard_id = torch.distributed.get_rank() else: shard_id = 0 self.input = ops.COCOReader(file_root=file_root, annotations_file=annotations_file, shard_id=shard_id, num_shards=num_gpus, ratio=True, ltrb=True, random_shuffle=True, skip_empty=True) self.decode = ops.ImageDecoder(device="cpu", output_type=types.RGB) # Augumentation techniques self.crop = ops.SSDRandomCrop(device="cpu", num_attempts=1) self.twist = ops.ColorTwist(device="gpu") self.resize = ops.Resize(device="gpu", resize_x=300, resize_y=300) output_dtype = types.FLOAT16 if output_fp16 else types.FLOAT output_layout = types.NHWC if output_nhwc else types.NCHW self.normalize = ops.CropMirrorNormalize(device="gpu", crop=(300, 300), mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], mirror=0, output_dtype=output_dtype, output_layout=output_layout, pad_output=pad_output) # Random variables self.rng1 = ops.Uniform(range=[0.5, 1.5]) self.rng2 = ops.Uniform(range=[0.875, 1.125]) self.rng3 = ops.Uniform(range=[-0.5, 0.5])
def __init__(self, args, device_id, file_root, annotations_file): super(DetectionPipeline, self).__init__(args.batch_size, args.num_workers, device_id, args.prefetch, args.seed) # Reading COCO dataset self.input = ops.COCOReader(file_root=file_root, annotations_file=annotations_file, shard_id=device_id, num_shards=args.num_gpus, ratio=True, ltrb=True, random_shuffle=True) self.decode_cpu = ops.HostDecoder(device="cpu", output_type=types.RGB) self.decode_crop = ops.HostDecoderSlice(device="cpu", output_type=types.RGB) self.decode_gpu = ops.nvJPEGDecoder(device="mixed", output_type=types.RGB) self.decode_gpu_crop = ops.nvJPEGDecoderSlice(device="mixed", output_type=types.RGB) self.ssd_crop = ops.SSDRandomCrop(device="cpu", num_attempts=1, seed=args.seed) self.random_bbox_crop = ops.RandomBBoxCrop( device="cpu", aspect_ratio=[0.5, 2.0], thresholds=[0, 0.1, 0.3, 0.5, 0.7, 0.9], scaling=[0.3, 1.0], ltrb=True, seed=args.seed) self.slice_cpu = ops.Slice(device="cpu") self.slice_gpu = ops.Slice(device="gpu") self.resize_cpu = ops.Resize( device="cpu", resize_x=300, resize_y=300, min_filter=types.DALIInterpType.INTERP_TRIANGULAR) self.resize_gpu = ops.Resize( device="gpu", resize_x=300, resize_y=300, min_filter=types.DALIInterpType.INTERP_TRIANGULAR) mean = [0.485 * 255, 0.456 * 255, 0.406 * 255] std = [0.229 * 255, 0.224 * 255, 0.225 * 255] crop_size = (300, 300) self.normalize_cpu = ops.CropMirrorNormalize(device="cpu", crop=crop_size, mean=mean, std=std, mirror=0, output_dtype=types.FLOAT) self.normalize_gpu = ops.CropMirrorNormalize(device="gpu", crop=crop_size, mean=mean, std=std, mirror=0, output_dtype=types.FLOAT) self.twist_cpu = ops.ColorTwist(device="cpu") self.twist_gpu = ops.ColorTwist(device="gpu") self.flip_cpu = ops.Flip(device="cpu") self.bbox_flip_cpu = ops.BbFlip(device="cpu", ltrb=True) self.flip_gpu = ops.Flip(device="gpu") self.bbox_flip_gpu = ops.BbFlip(device="gpu", ltrb=True) default_boxes = coco_anchors() self.box_encoder_cpu = ops.BoxEncoder(device="cpu", criteria=0.5, anchors=default_boxes) self.box_encoder_gpu = ops.BoxEncoder(device="gpu", criteria=0.5, anchors=default_boxes) self.box_encoder_cpu_offsets = ops.BoxEncoder( device="cpu", criteria=0.5, offset=True, scale=2, stds=[0.1, 0.1, 0.2, 0.2], anchors=default_boxes) self.box_encoder_gpu_offsets = ops.BoxEncoder( device="gpu", criteria=0.5, offset=True, scale=2, stds=[0.1, 0.1, 0.2, 0.2], anchors=default_boxes) # Random variables self.rng1 = ops.Uniform(range=[0.5, 1.5]) self.rng2 = ops.Uniform(range=[0.875, 1.125]) self.rng3 = ops.Uniform(range=[-0.5, 0.5])
def __init__(self, args, device_id, file_root, annotations_file): super(DetectionPipeline, self).__init__(batch_size=args.batch_size, num_threads=args.num_workers, device_id=device_id, prefetch_queue_depth=args.prefetch, seed=args.seed) # Reading COCO dataset self.input = ops.readers.COCO(file_root=file_root, annotations_file=annotations_file, shard_id=device_id, num_shards=args.num_gpus, ratio=True, ltrb=True, random_shuffle=True) self.decode_cpu = ops.decoders.Image(device="cpu", output_type=types.RGB) self.decode_crop = ops.decoders.ImageSlice(device="cpu", output_type=types.RGB) self.decode_gpu = ops.decoders.Image(device="mixed", output_type=types.RGB, hw_decoder_load=0) self.decode_gpu_crop = ops.decoders.ImageSlice(device="mixed", output_type=types.RGB, hw_decoder_load=0) self.ssd_crop = ops.SSDRandomCrop(device="cpu", num_attempts=1, seed=args.seed) self.random_bbox_crop = ops.RandomBBoxCrop( device="cpu", aspect_ratio=[0.5, 2.0], thresholds=[0, 0.1, 0.3, 0.5, 0.7, 0.9], scaling=[0.3, 1.0], bbox_layout="xyXY", seed=args.seed) self.slice_cpu = ops.Slice(device="cpu") self.slice_gpu = ops.Slice(device="gpu") self.resize_cpu = ops.Resize( device="cpu", resize_x=300, resize_y=300, min_filter=types.DALIInterpType.INTERP_TRIANGULAR) self.resize_gpu = ops.Resize( device="gpu", resize_x=300, resize_y=300, min_filter=types.DALIInterpType.INTERP_TRIANGULAR) mean = [0.485 * 255, 0.456 * 255, 0.406 * 255] std = [0.229 * 255, 0.224 * 255, 0.225 * 255] crop_size = (300, 300) self.normalize_cpu = ops.CropMirrorNormalize(device="cpu", crop=crop_size, mean=mean, std=std, mirror=0, dtype=types.FLOAT) self.normalize_gpu = ops.CropMirrorNormalize(device="gpu", crop=crop_size, mean=mean, std=std, mirror=0, dtype=types.FLOAT) self.twist_cpu = ops.ColorTwist(device="cpu") self.twist_gpu = ops.ColorTwist(device="gpu") self.hsv_cpu = ops.Hsv(device="cpu", dtype=types.FLOAT) self.hsv_gpu = ops.Hsv(device="gpu", dtype=types.FLOAT) self.bc_cpu = ops.BrightnessContrast(device="cpu", dtype=types.UINT8, contrast_center=128) self.bc_gpu = ops.BrightnessContrast(device="gpu", dtype=types.UINT8, contrast_center=128) self.flip_cpu = ops.Flip(device="cpu") self.bbox_flip_cpu = ops.BbFlip(device="cpu", ltrb=True) self.flip_gpu = ops.Flip(device="gpu") self.bbox_flip_gpu = ops.BbFlip(device="gpu", ltrb=True) default_boxes = coco_anchors() self.box_encoder_cpu = ops.BoxEncoder(device="cpu", criteria=0.5, anchors=default_boxes) self.box_encoder_gpu = ops.BoxEncoder(device="gpu", criteria=0.5, anchors=default_boxes) self.box_encoder_cpu_offsets = ops.BoxEncoder( device="cpu", criteria=0.5, offset=True, scale=2, stds=[0.1, 0.1, 0.2, 0.2], anchors=default_boxes) self.box_encoder_gpu_offsets = ops.BoxEncoder( device="gpu", criteria=0.5, offset=True, scale=2, stds=[0.1, 0.1, 0.2, 0.2], anchors=default_boxes) # Random variables self.saturation_rng = ops.random.Uniform(range=[0.8, 1.2]) self.contrast_rng = ops.random.Uniform(range=[0.5, 1.5]) self.brighness_rng = ops.random.Uniform(range=[0.875, 1.125]) self.hue_rng = ops.random.Uniform(range=[-45, 45])
def __init__(self, batch_size, device_id, file_root, annotations_file, num_gpus, output_fp16=False, output_nhwc=False, pad_output=False, num_threads=1, seed=15, dali_cache=-1, dali_async=True, use_nvjpeg=False, use_roi=False): super(COCOPipeline, self).__init__(batch_size=batch_size, device_id=device_id, num_threads=num_threads, seed=seed, exec_pipelined=dali_async, exec_async=dali_async) self.use_roi = use_roi self.use_nvjpeg = use_nvjpeg try: shard_id = torch.distributed.get_rank() except RuntimeError: shard_id = 0 self.input = ops.COCOReader(file_root=file_root, annotations_file=annotations_file, shard_id=shard_id, num_shards=num_gpus, ratio=True, ltrb=True, skip_empty=True, random_shuffle=(dali_cache > 0), stick_to_shard=(dali_cache > 0), shuffle_after_epoch=(dali_cache <= 0)) if use_nvjpeg: if use_roi: self.decode = ops.nvJPEGDecoderSlice(device="mixed", output_type=types.RGB) # handled in ROI decoder self.slice = None else: if dali_cache > 0: self.decode = ops.nvJPEGDecoder(device="mixed", output_type=types.RGB, cache_size=dali_cache * 1024, cache_type="threshold", cache_threshold=10000) else: self.decode = ops.nvJPEGDecoder(device="mixed", output_type=types.RGB) self.slice = ops.Slice(device="gpu") self.crop = ops.RandomBBoxCrop( device="cpu", aspect_ratio=[0.5, 2.0], thresholds=[0, 0.1, 0.3, 0.5, 0.7, 0.9], scaling=[0.3, 1.0], ltrb=True, allow_no_crop=True, num_attempts=1) else: self.decode = ops.HostDecoder(device="cpu", output_type=types.RGB) # handled in the cropper self.slice = None self.crop = ops.SSDRandomCrop(device="cpu", num_attempts=1) # Augumentation techniques (in addition to random crop) self.twist = ops.ColorTwist(device="gpu") self.resize = ops.Resize( device="gpu", resize_x=300, resize_y=300, min_filter=types.DALIInterpType.INTERP_TRIANGULAR) output_dtype = types.FLOAT16 if output_fp16 else types.FLOAT output_layout = types.NHWC if output_nhwc else types.NCHW mean_val = list(np.array([0.485, 0.456, 0.406]) * 255.) std_val = list(np.array([0.229, 0.224, 0.225]) * 255.) self.normalize = ops.CropMirrorNormalize(device="gpu", crop=(300, 300), mean=mean_val, std=std_val, mirror=0, output_dtype=output_dtype, output_layout=output_layout, pad_output=pad_output) # Random variables self.rng1 = ops.Uniform(range=[0.5, 1.5]) self.rng2 = ops.Uniform(range=[0.875, 1.125]) self.rng3 = ops.Uniform(range=[-0.5, 0.5])
def __init__(self, batch_size, device_id, file_root, annotations_file, num_gpus, output_fp16=False, output_nhwc=False, pad_output=False, num_threads=1, seed=15): super(COCOPipeline, self).__init__(batch_size=batch_size, device_id=device_id, num_threads=num_threads, seed=seed) if torch.distributed.is_initialized(): shard_id = torch.distributed.get_rank() else: shard_id = 0 self.input = ops.COCOReader(file_root=file_root, annotations_file=annotations_file, shard_id=shard_id, num_shards=num_gpus, ratio=True, ltrb=True, random_shuffle=True, skip_empty=True) self.decode = ops.ImageDecoder(device="cpu", output_type=types.RGB) # Augumentation techniques self.rotate = ops.Rotate(device="gpu", angle=30, interp_type=types.INTERP_LINEAR, fill_value=0) self.crop = ops.SSDRandomCrop(device="cpu", num_attempts=1) self.twist = ops.ColorTwist(device="gpu") self.resize = ops.Resize(device="gpu", resize_x=300, resize_y=300) # Will flip with probability provided in CoinFlip self.flip = ops.Flip(device='gpu') self.coin_flip_v = ops.CoinFlip(probability=0.1) self.coin_flip_h = ops.CoinFlip(probability=0.1) # bbox flipping self.bbflip = ops.BbFlip(device='gpu', ltrb=True) # paste self.paste = ops.Paste(device='gpu', fill_value=0) self.paste_pos = ops.Uniform(range=(0, 1)) self.paste_ratio = ops.Uniform(range=(1, 2)) self.bbpaste = ops.BBoxPaste(device='cpu', ltrb=True) # prospective self.prospective_crop = ops.RandomBBoxCrop( device='cpu', aspect_ratio=[0.5, 2.0], thresholds=[0.1, 0.3, 0.5], scaling=[0.8, 1.0], ltrb=True ) # slice (after prospective crop) self.slice = ops.Slice(device='gpu') # color self.water = ops.Water(device='gpu') # self.contrast = ops.BrightnessContrast(device="gpu", brightness=0.5, contrast=1.5) # self.hsv = ops.Hsv(device="gpu", hue=45., saturation=0.2) self.sphere = ops.Sphere(device='gpu') self.warpaffine = ops.WarpAffine(device="gpu", matrix=[1.0, 0.8, 0.0, 0.0, 1.2, 0.0], interp_type=types.INTERP_LINEAR) output_dtype = types.FLOAT16 if output_fp16 else types.FLOAT output_layout = types.NHWC if output_nhwc else types.NCHW self.normalize = ops.CropMirrorNormalize(device="gpu", crop=(300, 300), mean=[0.0, 0.0, 0.0], std=[255.0, 255.0, 255.0], mirror=0, output_dtype=output_dtype, output_layout=output_layout, pad_output=pad_output) # Random variables self.rng1 = ops.Uniform(range=[0.5, 1.5]) self.rng2 = ops.Uniform(range=[0.875, 1.125]) self.rng3 = ops.Uniform(range=[-0.5, 0.5])