def classification_model_resnet18_combine_last_var(**kwargs): base_model = pretrainedmodels.resnet18() return ClassificationModelResnetCombineLastVariable( base_model, base_model_features=512, nb_features=6, base_model_l1_outputs=64, **kwargs)
def segmentation_model_resnet18_bn_filters8_masked(**kwargs): base_model = pretrainedmodels.resnet18() return ResnetWeightedSegmentatation(base_model, DecoderBlock=DecoderBlockBN, nb_features=6, base_model_l1_outputs=64, filters=8, **kwargs)
def segmentation_model_resnet18_bn_filters8(**kwargs): base_model = pretrainedmodels.resnet18() return ClassificationModelResnetCombineLastVariable3( base_model, DecoderBlock=DecoderBlockBN, nb_features=6, base_model_l1_outputs=64, filters=8, **kwargs)
def __init__(self, weight='imagenet'): super(DiscriminatorModel, self).__init__() self.layer = nn.Conv2d(1, 3, (2, 2), padding=2) model = cm.resnet18(num_classes=1000, pretrained=weight) model.last_linear = nn.Linear(in_features=512, out_features=1, bias=True) self.model = model
def __init__(self, num_classes, pretrained="imagenet"): super().__init__() self.model = resnet18(pretrained=pretrained) self.model.avg_pool = nn.AdaptiveAvgPool2d(1) new_last_linear = nn.Linear(self.model.last_linear.in_features, num_classes) new_last_linear.weight.data = self.model.last_linear.weight.data[: num_classes] new_last_linear.bias.data = self.model.last_linear.bias.data[: num_classes] self.model.last_linear = new_last_linear
def __init__(self): #扩展的VGG super(VGG, self).__init__() self.model = pretrainedmodels.resnet18() in_dim = self.model.last_linear.in_features classifier = torch.nn.Sequential(torch.nn.Linear(in_dim, 448), torch.nn.ReLU(), torch.nn.Dropout(0.2), torch.nn.Linear(448, 15)) self.model.last_linear = classifier for param in self.parameters(): param.require_grad = True
def __init__(self): super().__init__() resnet = pretrainedmodels.resnet18() self.a = nn.Sequential( resnet.conv1, resnet.bn1, resnet.relu, ) self.b = nn.Sequential( resnet.maxpool, resnet.layer1, ) self.c = resnet.layer2 self.d = resnet.layer3
def load_models(conf_file): out = {} with open(conf_file) as f: doc = yaml.full_load(f) conf = doc['config'] for k, stat in conf.items(): if stat['net'] == 'inception_v4': out[k] = (pretrainedmodels.inceptionv4(pretrained=None), stat['sparisity']) elif stat['net'] == 'resnet18': out[k] = (pretrainedmodels.resnet18(pretrained=None), stat['sparisity']) elif stat['net'] == 'mobilenet_v2': out[k] = (models.mobilenet_v2(), stat['sparisity']) else: raise "Unknown net" return out
def _get_branch_net(self, channels, num_classes): model = resnet18(pretrained="imagenet") model.global_pool = nn.AdaptiveAvgPool2d(1) model.conv1_7x7_s2 = nn.Conv2d(channels, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3)) model.last_linear = nn.Sequential( nn.BatchNorm1d(1024), nn.Dropout(0.5), nn.Linear(1024, num_classes), ) # print('Model architecture:') # print(model) # total_params = sum(p.numel() for p in model.parameters() if p.requires_grad) # print(f'\n\n\n\nModel trainable parameters {total_params}') return model
def resnet18(input_size=(3, 224, 224), num_classes=1000, pretrained=None): model = models.resnet18(pretrained=pretrained) model = add_instances_to_torchvisionmodel(model) # Change the First Convol2D layer into new input shape if input_size != (3, 224, 224): model.conv1 = nn.Conv2d(input_size[0], 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) model.input_size = input_size del model.fc del model.avgpool # calc kernel_size on new_avgpool2d layer test_tensor = torch.randn((1, input_size[0], input_size[1], input_size[2])) features = model.features(test_tensor) # print(features, features.shape[2], features.shape[3]) avg_pool2d_kernel_size = (features.shape[2], features.shape[3]) # calc last linear size x = F.avg_pool2d(features, kernel_size=avg_pool2d_kernel_size) x = x.view(x.size(0), -1).shape[1] model.last_linear = nn.Linear(in_features=x, out_features=num_classes) ##del model.logits ##del model.forward def logits(self, features): x = F.relu(features, inplace=False) x = F.avg_pool2d(x, kernel_size=avg_pool2d_kernel_size, stride=1) x = x.view(x.size(0), -1) x = self.last_linear(x) return x def forward(self, input): x = self.features(input) x = self.logits(x) return x model.logits = types.MethodType(logits, model) model.forward = types.MethodType(forward, model) return model
def get_resnet18(): model = resnet18() w = model.conv1.weight w = torch.nn.Parameter( torch.cat((w, torch.mean(w, dim=1).unsqueeze(1)), dim=1)) model.conv1 = nn.Conv2d(4, 64, kernel_size=7, stride=2, padding=3, bias=False) model.conv1.weight = w model.avgpool = nn.Sequential(nn.AvgPool2d(9, stride=1), nn.AvgPool2d(7, stride=1)) model.fc = nn.Sequential(nn.Dropout(), nn.Linear(2048, 28)) return model
def __init__(self, nb_embeddings=config.NB_EMBEDDINGS): super().__init__() self.base_model = pretrainedmodels.resnet18() self.fc = nn.Linear(2048, nb_embeddings)
params['feat_path'], params['logit_name'] + ('' if '.hdf5' in params['logit_name'] else '.hdf5')) print('Model: %s' % params['model']) print('The extracted features will be saved to --> %s' % params['feat_dir']) if params['model'] == 'resnet101': C, H, W = 3, 224, 224 model = pretrainedmodels.resnet101(pretrained='imagenet') elif params['model'] == 'resnet152': C, H, W = 3, 224, 224 model = pretrainedmodels.resnet152(pretrained='imagenet') elif params['model'] == 'resnet18': C, H, W = 3, 224, 224 model = pretrainedmodels.resnet18(pretrained='imagenet') elif params['model'] == 'resnet34': C, H, W = 3, 224, 224 model = pretrainedmodels.resnet34(pretrained='imagenet') elif params['model'] == 'inceptionresnetv2': C, H, W = 3, 299, 299 model = pretrainedmodels.inceptionresnetv2( num_classes=1001, pretrained='imagenet+background') elif params['model'] == 'googlenet': C, H, W = 3, 224, 224 model = googlenet(pretrained=True) print(model) else: print("doesn't support %s" % (params['model'])) if params['model'] != 'googlenet':
def __init__(self, backbone, heads, head_conv=128, num_filters=[256, 256, 256], pretrained=True, dcn=False, gn=False, ws=False, freeze_bn=False, after_non_local='layer1', non_local_hidden_channels=None): super().__init__() self.heads = heads if backbone == 'resnet18': pretrained = 'imagenet' if pretrained else None self.backbone = pretrainedmodels.resnet18(pretrained=pretrained) num_bottleneck_filters = 512 elif backbone == 'resnet34': pretrained = 'imagenet' if pretrained else None self.backbone = pretrainedmodels.resnet34(pretrained=pretrained) num_bottleneck_filters = 512 elif backbone == 'resnet50': pretrained = 'imagenet' if pretrained else None self.backbone = pretrainedmodels.resnet50(pretrained=pretrained) num_bottleneck_filters = 2048 elif backbone == 'resnet101': pretrained = 'imagenet' if pretrained else None self.backbone = pretrainedmodels.resnet101(pretrained=pretrained) num_bottleneck_filters = 2048 elif backbone == 'resnet152': pretrained = 'imagenet' if pretrained else None self.backbone = pretrainedmodels.resnet152(pretrained=pretrained) num_bottleneck_filters = 2048 elif backbone == 'se_resnext50_32x4d': pretrained = 'imagenet' if pretrained else None self.backbone = pretrainedmodels.se_resnext50_32x4d( pretrained=pretrained) num_bottleneck_filters = 2048 elif backbone == 'se_resnext101_32x4d': pretrained = 'imagenet' if pretrained else None self.backbone = pretrainedmodels.se_resnext101_32x4d( pretrained=pretrained) num_bottleneck_filters = 2048 elif backbone == 'resnet34_v1b': self.backbone = timm.create_model('gluon_resnet34_v1b', pretrained=pretrained) convert_to_inplace_relu(self.backbone) num_bottleneck_filters = 512 elif backbone == 'resnet50_v1d': self.backbone = timm.create_model('gluon_resnet50_v1d', pretrained=pretrained) convert_to_inplace_relu(self.backbone) num_bottleneck_filters = 2048 elif backbone == 'resnet101_v1d': self.backbone = timm.create_model('gluon_resnet101_v1d', pretrained=pretrained) convert_to_inplace_relu(self.backbone) num_bottleneck_filters = 2048 elif backbone == 'resnext50_32x4d': self.backbone = timm.create_model('resnext50_32x4d', pretrained=pretrained) convert_to_inplace_relu(self.backbone) num_bottleneck_filters = 2048 elif backbone == 'resnext50d_32x4d': self.backbone = timm.create_model('resnext50d_32x4d', pretrained=pretrained) convert_to_inplace_relu(self.backbone) num_bottleneck_filters = 2048 elif backbone == 'seresnext26_32x4d': self.backbone = timm.create_model('seresnext26_32x4d', pretrained=pretrained) convert_to_inplace_relu(self.backbone) num_bottleneck_filters = 2048 elif backbone == 'resnet18_ctdet': self.backbone = models.resnet18() state_dict = torch.load( 'pretrained_weights/ctdet_coco_resdcn18.pth')['state_dict'] self.backbone.load_state_dict(state_dict, strict=False) num_bottleneck_filters = 512 elif backbone == 'resnet50_maskrcnn': self.backbone = models.detection.maskrcnn_resnet50_fpn( pretrained=pretrained).backbone.body print(self.backbone) num_bottleneck_filters = 2048 else: raise NotImplementedError if after_non_local is not None: self.after_non_local = after_non_local in_channels = getattr(self.backbone, after_non_local)[0].conv1.in_channels if non_local_hidden_channels is None: non_local_hidden_channels = in_channels // 2 self.non_local = NonLocal2d(in_channels, non_local_hidden_channels) if freeze_bn: for m in self.backbone.modules(): if isinstance(m, nn.BatchNorm2d): m.weight.requires_grad = False m.bias.requires_grad = False self.lateral4 = nn.Sequential( Conv2d(num_bottleneck_filters, num_filters[0], kernel_size=1, bias=False, ws=ws), nn.GroupNorm(32, num_filters) if gn else nn.BatchNorm2d(num_filters[0]), nn.ReLU(inplace=True)) self.lateral3 = nn.Sequential( Conv2d(num_bottleneck_filters // 2, num_filters[0], kernel_size=1, bias=False, ws=ws), nn.GroupNorm(32, num_filters[0]) if gn else nn.BatchNorm2d(num_filters[0]), nn.ReLU(inplace=True)) self.lateral2 = nn.Sequential( Conv2d(num_bottleneck_filters // 4, num_filters[1], kernel_size=1, bias=False, ws=ws), nn.GroupNorm(32, num_filters[1]) if gn else nn.BatchNorm2d(num_filters[1]), nn.ReLU(inplace=True)) self.lateral1 = nn.Sequential( Conv2d(num_bottleneck_filters // 8, num_filters[2], kernel_size=1, bias=False, ws=ws), nn.GroupNorm(32, num_filters) if gn else nn.BatchNorm2d(num_filters[2]), nn.ReLU(inplace=True)) self.decode3 = nn.Sequential( DCN(num_filters[0], num_filters[1], kernel_size=3, padding=1, stride=1) if dcn else \ Conv2d(num_filters[0], num_filters[1], kernel_size=3, padding=1, bias=False, ws=ws), nn.GroupNorm(32, num_filters[1]) if gn else nn.BatchNorm2d(num_filters[1]), nn.ReLU(inplace=True)) self.decode2 = nn.Sequential( Conv2d(num_filters[1], num_filters[2], kernel_size=3, padding=1, bias=False, ws=ws), nn.GroupNorm(32, num_filters[2]) if gn else nn.BatchNorm2d(num_filters[2]), nn.ReLU(inplace=True)) self.decode1 = nn.Sequential( Conv2d(num_filters[2], num_filters[2], kernel_size=3, padding=1, bias=False, ws=ws), nn.GroupNorm(32, num_filters[2]) if gn else nn.BatchNorm2d(num_filters[2]), nn.ReLU(inplace=True)) for head in sorted(self.heads): num_output = self.heads[head] fc = nn.Sequential( Conv2d(num_filters[2], head_conv, kernel_size=3, padding=1, bias=False, ws=ws), nn.GroupNorm(32, head_conv) if gn else nn.BatchNorm2d(head_conv), nn.ReLU(inplace=True), nn.Conv2d(head_conv, num_output, kernel_size=1)) if 'hm' in head: fc[-1].bias.data.fill_(-2.19) else: fill_fc_weights(fc) self.__setattr__(head, fc)
def Model_builder(configer): model_name = configer.model['name'] No_classes = configer.dataset_cfg["id_cfg"]["num_classes"] model_pretrained = configer.model['pretrained'] model_dataparallel = configer.model["DataParallel"] model_gpu_replica = configer.model["Multi_GPU_replica"] gpu_ids = configer.train_cfg["gpu"] if model_name == "Inceptionv3": model = PM.inceptionv3(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "Xception": model = PM.xception(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "VGG_19": model = PM.vgg19(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "Resnet18": model = PM.resnet18(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "Resnet50": model = PM.resnet50(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "Resnet101": model = PM.resnet101(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "Resnet152": model = PM.resnet152(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "Resnet34": model = PM.resnet34(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "Densenet121": model = PM.densenet121(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "ResNeXt101-32": model = PM.resnext101_32x4d(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "ResNeXt101-64": model = PM.resnext101_64x4d(num_classes=1000, pretrained=model_pretrained) d = model.last_linear.in_features model.last_linear = nn.Linear(d, No_classes) elif model_name == "MobilenetV2": model = MobileNetV2(n_class=No_classes) else: raise ImportError("Model Architecture not supported") # Performing Data Parallelism if configured if model_dataparallel: model = torch.nn.DataParallel(model.to(device), device_ids=gpu_ids) elif model_gpu_replica: torch.distributed.init_process_group(backend='nccl', world_size=1, rank=1) model = torch.nn.DistributedDataParallel(model.to(device), device_ids=gpu_ids) else: model = model.to(device) print('---------- Model Loaded') return model
def get_base_model(config): model_name = config.backbone pretrained = config.pretrained if pretrained is not None and pretrained != 'imagenet': weights_path = pretrained pretrained = None else: weights_path = None if config.multibranch: input_channels = config.multibranch_input_channels else: input_channels = config.num_slices if hasattr(config, 'append_masks') and config.append_masks: input_channels *= 2 _available_models = ['senet154', 'se_resnext50', 'resnet34', 'resnet18'] if model_name == 'senet154': cut_point = -3 model = nn.Sequential( *list(pretrainedmodels.senet154( pretrained=pretrained).children())[:cut_point]) num_features = 2048 elif model_name == 'se_resnext50': cut_point = -2 model = nn.Sequential(*list( pretrainedmodels.se_resnext50_32x4d( pretrained=pretrained).children())[:cut_point]) num_features = 2048 elif model_name == 'resnet34': cut_point = -2 model = nn.Sequential( *list(pretrainedmodels.resnet34( pretrained=pretrained).children())[:cut_point]) num_features = 512 elif model_name == 'resnet18': cut_point = -2 model = nn.Sequential( *list(pretrainedmodels.resnet18( pretrained=pretrained).children())[:cut_point]) num_features = 512 else: raise ValueError('Unavailable backbone, choose one from {}'.format( _available_models)) if model_name in ['senet154', 'se_resnext50']: conv1 = model[0].conv1 else: conv1 = model[0] if input_channels != 3: conv1_weights = deepcopy(conv1.weight) new_conv1 = nn.Conv2d(input_channels, conv1.out_channels, kernel_size=conv1.kernel_size, stride=conv1.stride, padding=conv1.padding, bias=conv1.bias) if weights_path is None: if input_channels == 1: new_conv1.weight.data.fill_(0.) new_conv1.weight[:, 0, :, :].data.copy_(conv1_weights[:, 0, :, :]) elif input_channels > 3: diff = (input_channels - 3) // 2 new_conv1.weight.data.fill_(0.) new_conv1.weight[:, diff:diff + 3, :, :].data.copy_(conv1_weights) if model_name in ['senet154', 'se_resnext50']: model[0].conv1 = new_conv1 else: model[0] = new_conv1 if weights_path is not None: if model_name in ['senet154', 'se_resnext50']: conv1_str = '0.conv1.weight' else: conv1_str = '0.weight' weights = load_base_weights(weights_path, input_channels, conv1_str) model.load_state_dict(weights) return model, num_features
def __init__(self, config_file: Optional[str] = None, override_list: List[Any] = []): _C = CN() _C.VALID_IMAGES = [ 'CXR1576_IM-0375-2001.png', 'CXR1581_IM-0378-2001.png', 'CXR3177_IM-1497-2001.png', 'CXR2585_IM-1082-1001.png', 'CXR1125_IM-0082-1001.png', 'CXR3_IM-1384-2001.png', 'CXR1565_IM-0368-1001.png', 'CXR1105_IM-0072-1001-0001.png', 'CXR2874_IM-1280-1001.png', 'CXR1886_IM-0574-1001.png' ] _C.MODELS = [{ 'resnet18': (pretrainedmodels.resnet18(pretrained=None), 512, 224), 'resnet50': (pretrainedmodels.resnet50(pretrained=None), 2048, 224), 'resnet101': (pretrainedmodels.resnet101(pretrained=None), 2048, 224), 'resnet152': (pretrainedmodels.resnet152(pretrained=None), 2048, 224), 'inception_resnet_v2': (pretrainedmodels.inceptionresnetv2(pretrained=None), 1536, 299) }] # _C.MODELS_FEATURE_SIZE = {'resnet18':512, 'resnet50':2048, 'resnet101':2048, 'resnet152':2048, # 'inception_v3':2048, 'inception_resnet_v2':1536} # Random seed for NumPy and PyTorch, important for reproducibility. _C.RANDOM_SEED = 42 # Opt level for mixed precision training using NVIDIA Apex. This can be # one of {0, 1, 2}. Refer NVIDIA Apex docs for their meaning. _C.FP16_OPT = 2 # Path to the dataset root, which structure as per README. Path is # assumed to be relative to project root. _C.IMAGE_PATH = '/netscratch/gsingh/MIMIC_CXR/DataSet/Indiana_Chest_XRay/Images_2' _C.TRAIN_JSON_PATH = '/netscratch/gsingh/MIMIC_CXR/DataSet/Indiana_Chest_XRay/iu_xray_train_2.json' _C.VAL_JSON_PATH = '/netscratch/gsingh/MIMIC_CXR/DataSet/Indiana_Chest_XRay/iu_xray_val_2.json' _C.TEST_JSON_PATH = '/netscratch/gsingh/MIMIC_CXR/DataSet/Indiana_Chest_XRay/iu_xray_test_2.json' _C.PRETRAINED_EMDEDDING = False # Path to .vocab file generated by ``sentencepiece``. _C.VOCAB_FILE_PATH = "/netscratch/gsingh/MIMIC_CXR/DataSet/Indiana_Chest_XRay/Vocab/indiana.vocab" # Path to .model file generated by ``sentencepiece``. _C.VOCAB_MODEL_PATH = "/netscratch/gsingh/MIMIC_CXR/DataSet/Indiana_Chest_XRay/Vocab/indiana.model" _C.VOCAB_SIZE = 3000 _C.EPOCHS = 1024 _C.BATCH_SIZE = 10 _C.TEST_BATCH_SIZE = 100 _C.ITERATIONS_PER_EPOCHS = 1 _C.WEIGHT_DECAY = 1e-5 _C.NUM_LABELS = 41 _C.IMAGE_SIZE = 299 _C.MAX_SEQUENCE_LENGTH = 130 _C.DROPOUT_RATE = 0.1 _C.D_HEAD = 64 _C.TRAIN_DATASET_LENGTH = 25000 _C.INFERENCE_TIME = False _C.COMBINED_N_LAYERS = 1 _C.BEAM_SIZE = 50 _C.PADDING_INDEX = 0 _C.EOS_INDEX = 3 _C.SOS_INDEX = 2 _C.USE_BEAM_SEARCH = True _C.EXTRACTED_FEATURES = False _C.IMAGE_MODEL_PATH = '/netscratch/gsingh/MIMIC_CXR/Results/Image_Feature_Extraction/MIMIC_CXR_No_ES/model.pth' _C.EMBEDDING_DIM = 8192 _C.CONTEXT_SIZE = 1024 _C.LR_COMBINED = 1e-4 _C.MAX_LR = 1e-1 _C.SAVED_DATASET = False _C.MODEL_NAME = 'inception_resnet_v2' INIT_PATH = '/netscratch/gsingh/MIMIC_CXR/Results/Modified_Transformer/Indiana_15_10_2020_2/' _C.SAVED_DATASET_PATH_TRAIN = INIT_PATH + 'DataSet/train_dataloader.pth' _C.SAVED_DATASET_PATH_VAL = INIT_PATH + 'DataSet/val_dataloader.pth' _C.SAVED_DATASET_PATH_TEST = INIT_PATH + 'DataSet/test_dataloader.pth' _C.CHECKPOINT_PATH = INIT_PATH + 'CheckPoints' _C.MODEL_PATH = INIT_PATH + 'combined_model.pth' _C.MODEL_STATE_DIC = INIT_PATH + 'combined_model_state_dic.pth' _C.FIGURE_PATH = INIT_PATH + 'Graphs' _C.CSV_PATH = INIT_PATH _C.TEST_CSV_PATH = INIT_PATH + 'test_output_image_feature_input.json' self._C = _C if config_file is not None: self._C.merge_from_file(config_file) self._C.merge_from_list(override_list) self.add_derived_params() # Make an instantiated object of this class immutable. self._C.freeze()
# 指定RGB三个通道的均值和方差来将图像通道归一化 normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) train_augs = transforms.Compose([ transforms.RandomResizedCrop(size=224), transforms.RandomHorizontalFlip(), transforms.ToTensor(), normalize ]) test_augs = transforms.Compose([ transforms.Resize(size=256), transforms.CenterCrop(size=224), transforms.ToTensor(), normalize ]) pretrained_net = pretrainedmodels.resnet18() # fc是输出层函数 # 源码:self.fc = nn.Linear(512 * block.expansion, num_classes) pretrained_net.fc = nn.Linear(512, 2) output_params = list(map(id, pretrained_net.fc.parameters())) feature_params = filter(lambda p: id(p) not in output_params, pretrained_net.parameters()) lr = 0.01 optimizer = optim.SGD([{ 'params': feature_params }, { 'params': pretrained_net.fc.parameters(), 'lr': lr * 10 }],