diff --git a/app.db b/app.db index 7c78ae2..f017e0e 100644 Binary files a/app.db and b/app.db differ diff --git a/backend/app.go b/backend/app.go index 89a6a36..925a989 100644 --- a/backend/app.go +++ b/backend/app.go @@ -44,7 +44,6 @@ func (a *App) Startup(ctx context.Context) { a.ctx = ctx // 设置 ONNX Runtime DLL 路径 - // ort.SetSharedLibraryPath("onnxruntime.dll") exeDir, _ := os.Executable() println("exeDir", exeDir) ort.SetSharedLibraryPath(filepath.Join(filepath.Dir(exeDir), "onnxruntime.dll")) @@ -160,7 +159,6 @@ func (a *App) GormDB() (*gorm.DB, error) { } func (a *App) UploadImage(data []byte, filename string) Response { - println("UploadImage") uploadsDir := publicImagePath err := os.MkdirAll(uploadsDir, 0755) if err != nil { diff --git a/core/const/const.py b/core/const/const.py index eeab665..cb97821 100644 --- a/core/const/const.py +++ b/core/const/const.py @@ -26,22 +26,25 @@ if mode == "toy": ] num_classes = len(label_name) elif mode == "benchmark": - epoch = 100 # convnext->100, resnet18->50 - lr = 1e-4 + epoch = 50 # resnet=80, resnet18=50, convnext=100 + lr = 1e-4 # resnet, resnet18=1e-4 + weight_decay = 1e-4 # resnet=1e-3, resnet18=1e-4 batch_size = 8 input_size = 224 # 分类 label_name = [ - "american_shorthair", - "bengal", - "british_shorthair", - "exotic_shorthair", - "maine_coon", - "ragdoll", - "scottish_fold", - "siamese", - "sphynx", - "turkish_van", + "american_shorthair", # 美国短毛猫 + "british_shorthair", # 英国短毛猫 + "ragdoll", # 布偶猫 + "exotic_shorthair", # 异国短毛猫 + "maine_coon", # 缅因猫 + "siamese", # 暹罗猫 + "sphynx", # 斯芬克斯猫 + "turkish_van", # 土耳其梵猫 + "bengal", # 孟加拉豹猫 + "scottish_fold", # 苏格兰折耳猫 + "none", # 风景人物 + "other", # 其他动物 ] num_classes = len(label_name) \ No newline at end of file diff --git a/core/dataloader/dataloader.py b/core/dataloader/dataloader.py index 0399b42..9671218 100644 --- a/core/dataloader/dataloader.py +++ b/core/dataloader/dataloader.py @@ -76,4 +76,5 @@ print("test_dataset", len(test_dataset)) train_dataloader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True, num_workers=4) -test_dataloader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False, num_workers=4) \ No newline at end of file +test_dataloader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False, num_workers=4) + diff --git a/core/models/resnet_epoch_100.onnx b/core/models/resnet_epoch_100.onnx deleted file mode 100644 index 83bf702..0000000 Binary files a/core/models/resnet_epoch_100.onnx and /dev/null differ diff --git a/core/static/dataset_stats.csv b/core/static/dataset_stats.csv deleted file mode 100644 index eee661e..0000000 --- a/core/static/dataset_stats.csv +++ /dev/null @@ -1,67 +0,0 @@ -class,image_count,avg_width,avg_height,min_width,min_height,max_width,max_height,formats,corrupt_files -abyssinian,200,148,117,88,46,162,140,"jpeg, png",0 -cyprus,200,159,100,93,40,162,140,"jpeg, png",0 -lykoi,200,142,122,68,55,162,140,"jpeg, png",0 -donskoy,200,141,123,67,54,162,140,jpeg,0 -chausie,200,143,119,78,46,162,140,"jpeg, png",0 -european_shorthair,200,149,118,70,49,162,140,"jpeg, png",0 -turkish_van,200,149,120,87,56,162,140,"jpeg, png",0 -pixie_bob,200,147,119,78,49,162,140,"jpeg, png",0 -ragdoll,199,149,116,78,50,162,140,jpeg,0 -german_rex,199,138,125,72,50,162,140,"jpeg, png",0 -american_shorthair,199,147,114,65,50,162,140,"jpeg, png",0 -sokoke,199,145,122,70,49,162,140,"jpeg, png",0 -khao_manee,198,144,120,78,49,162,140,"jpeg, png",0 -thai,198,143,118,68,60,162,140,"jpeg, png",0 -cymric,198,148,120,63,43,162,140,"jpeg, png",0 -oriental_shorthair,197,141,123,78,54,162,140,jpeg,0 -cornish_rex,197,147,117,75,56,162,140,"jpeg, png",0 -burmese,197,147,117,45,58,162,140,"jpeg, png",0 -savannah,197,153,106,78,40,162,140,"jpeg, png",0 -american_wirehair,196,149,117,76,50,162,140,"jpeg, png",0 -peterbald,196,144,123,77,50,162,140,"jpeg, png",0 -karelian_bobtail,196,145,125,67,65,162,140,"jpeg, png",0 -tonkinese,195,148,116,70,53,162,140,"jpeg, png",0 -balinese,195,154,112,79,54,162,140,jpeg,0 -japanese_bobtail,194,149,118,87,49,162,140,"jpeg, png",0 -nebelung,194,143,119,64,46,162,140,jpeg,0 -selkirk_rex,192,144,122,78,76,162,140,jpeg,0 -persian,192,150,114,78,46,162,140,jpeg,0 -manx,192,155,113,86,50,162,140,"jpeg, png",0 -himalayan,192,158,109,93,40,162,140,jpeg,0 -munchkin,191,147,117,61,48,162,140,jpeg,0 -bengal,189,151,115,78,71,162,140,jpeg,0 -turkish_angora,188,145,119,66,52,162,140,jpeg,0 -vankedisi,187,147,116,63,47,162,140,"jpeg, png",0 -scottish_fold,184,143,120,78,50,162,140,jpeg,0 -egyptian_mau,184,144,121,72,74,162,140,"jpeg, png",0 -ocicat,182,150,115,62,44,162,140,"jpeg, png",0 -ragamuffin,182,149,116,78,44,162,140,"jpeg, png",0 -serengeti,175,159,100,78,53,300,140,"jpeg, png",0 -british_shorthair,174,148,117,78,50,162,140,jpeg,0 -toyger,160,145,120,78,50,162,140,"jpeg, png",0 -siberian,159,153,116,78,55,162,140,jpeg,0 -havana_brown,159,133,127,75,34,300,140,"jpeg, png",0 -exotic_shorthair,157,148,118,93,55,300,140,"jpeg, png",0 -bombay,154,139,123,46,50,162,140,"jpeg, png",0 -korat,152,147,117,93,50,162,140,"jpeg, png",0 -safari,150,158,105,79,38,300,140,"jpeg, png",0 -american_bobtail,140,155,114,64,48,162,140,jpeg,0 -mekong_bobtail,140,149,118,44,50,162,140,"jpeg, png",0 -korean_bobtail,139,140,129,63,81,162,140,jpeg,0 -siamese,139,152,115,78,53,300,140,"jpeg, png",0 -somali,139,150,112,61,53,162,140,jpeg,0 -devon_rex,138,150,116,78,55,162,140,jpeg,0 -american_curl,138,155,112,91,51,300,140,"jpeg, png",0 -ural_rex,137,144,121,48,65,162,140,"jpeg, png",0 -singapura,136,158,109,93,54,300,140,"jpeg, png",0 -ukrainian_levkoy,134,140,123,78,59,162,140,jpeg,0 -maine_coon,133,141,122,66,79,162,140,jpeg,0 -birman,131,155,113,93,56,162,140,jpeg,0 -oregon_rex,121,147,123,85,66,300,140,"jpeg, png",0 -kurilian_bobtail,120,149,121,78,81,162,140,jpeg,0 -laperm,120,149,116,78,55,162,140,"jpeg, png",0 -sphynx,120,149,117,47,63,162,140,jpeg,0 -chartreux,114,146,117,75,61,162,140,jpeg,0 -russian_blue,109,152,111,88,36,162,140,jpeg,0 -norwegian_forest_cat,97,150,114,78,56,162,140,jpeg,0 diff --git a/core/test/test_onnx.py b/core/test/test_onnx.py index 7b7193b..9755bc0 100644 --- a/core/test/test_onnx.py +++ b/core/test/test_onnx.py @@ -4,13 +4,12 @@ import glob import torch import numpy as np from PIL import Image -import onnxruntime as ort # 【修改1】替换torch导入 -from torchvision import transforms # 保留transforms，仍用于预处理 +import onnxruntime as ort +from torchvision import transforms from core.const import mode, label_name, input_size def test(): - # 【修改2】选择ONNX Runtime的执行提供程序，自动选择CPU或CUDA providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if 'CUDAExecutionProvider' in ort.get_available_providers() else ['CPUExecutionProvider'] print(f"使用设备: {providers[0]}") @@ -19,7 +18,7 @@ def test(): model_dir = os.path.join(core_dir, "models") dataset_dir = os.path.join(core_dir, "dataset", mode, "test") - # 【修改3】加载ONNX模型，替代原来的PyTorch模型加载 + # 加载ONNX模型 session = ort.InferenceSession(os.path.join(model_dir, "resnet_epoch_100.onnx"), providers=providers) # 获取输入名称（用于后续推理时指定输入） @@ -28,7 +27,7 @@ def test(): im_list = glob.glob(os.path.join(dataset_dir, "*", "*.jpg")) np.random.shuffle(im_list) - # 预处理完全不变 + # 预处理 test_transform = transforms.Compose([ transforms.Resize(input_size), transforms.CenterCrop(input_size), @@ -42,15 +41,15 @@ def test(): inputs = test_transform(im_data) inputs = torch.unsqueeze(inputs, dim=0) # 这里还在用torch，下面会改 - # 【修改4】将输入转为numpy，ONNX Runtime需要numpy输入 + # 将输入转为numpy，ONNX Runtime需要numpy输入 inputs = inputs.numpy() if providers[0] == 'CPUExecutionProvider': inputs = inputs.astype(np.float32) - # 【修改5】ONNX Runtime推理，输出直接是numpy数组 + # ONNX Runtime推理，输出直接是numpy数组 outputs = session.run(None, {input_name: inputs})[0] - # 【修改6】解析结果，直接用numpy操作 + # 解析结果，直接用numpy操作 pred = np.argmax(outputs, axis=1) print(label_name[pred[0]], " ", im_path) diff --git a/core/test/test_resnet.py b/core/test/test_resnet.py index d2c8158..1ac334a 100644 --- a/core/test/test_resnet.py +++ b/core/test/test_resnet.py @@ -21,7 +21,7 @@ def test(): print("model_dir", model_dir) net = resnet() - net.load_state_dict(torch.load(os.path.join(model_dir, "resnet_epoch_99.pth"), weights_only=True)) + net.load_state_dict(torch.load(os.path.join(model_dir, "resnet_epoch_80.pth"), weights_only=True)) print("111") diff --git a/core/test/test_resnet18.py b/core/test/test_resnet18.py index c994300..b394939 100644 --- a/core/test/test_resnet18.py +++ b/core/test/test_resnet18.py @@ -18,10 +18,8 @@ def test(): model_dir = os.path.join(core_dir, "models") dataset_dir = os.path.join(core_dir, "dataset", mode, "test") - print("model_dir", model_dir) - net = resnet18() - net.load_state_dict(torch.load(os.path.join(model_dir, "resnet18_epoch_50_bak2.pth"), weights_only=True)) + net.load_state_dict(torch.load(os.path.join(model_dir, "resnet18_epoch_50.pth"), weights_only=True)) im_list = glob.glob(os.path.join(dataset_dir, "*", "*.jpg")) np.random.shuffle(im_list) @@ -35,6 +33,8 @@ def test(): transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]) + ary = [] + errors = [] for im_path in im_list: net.eval() im_data = Image.open(im_path) @@ -46,13 +46,25 @@ def test(): outputs = net.forward(inputs) _, pred = torch.max(outputs.data, dim=1) - print(label_name[pred.cpu().numpy()[0]], " ", im_path) + # print(label_name[pred.cpu().numpy()[0]], " ", im_path) - img = np.asarray(im_data) - img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR) - img = cv2.resize(img, (200, 200)) - cv2.imshow("img", img) - cv2.waitKey(0) + # img = np.asarray(im_data) + # img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR) + # img = cv2.resize(img, (200, 200)) + # cv2.imshow("img", img) + # cv2.waitKey(0) + result = label_name[pred.cpu().numpy()[0]] + + if result in im_path: + ary.append(True) + else: + ary.append(False) + print(f"{label_name[pred.cpu().numpy()[0]]} {im_path}\n") + errors.append(f"{label_name[pred.cpu().numpy()[0]]} {im_path}") + + print("ary", ary) + # print("errors", errors) + print(sum(ary) / len(ary)) if __name__ == "__main__": diff --git a/core/train/train_resnet.py b/core/train/train_resnet.py index 89ee1cc..d4bc7d4 100644 --- a/core/train/train_resnet.py +++ b/core/train/train_resnet.py @@ -2,7 +2,7 @@ import os import torch from core.nets.resnet import resnet from core.dataloader.dataloader import train_dataloader -from core.const import epoch, lr, batch_size +from core.const import epoch, lr, weight_decay, batch_size def train(): @@ -13,9 +13,9 @@ def train(): loss_func = torch.nn.CrossEntropyLoss() - optimizer = torch.optim.Adam(net.parameters(), lr=lr) + optimizer = torch.optim.Adam(net.parameters(), lr=lr, weight_decay=weight_decay) - scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.5) + scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=20, gamma=0.5) for e in range(epoch): print("epoch: ", e) diff --git a/core/train/train_resnet18.py b/core/train/train_resnet18.py index b42fe69..b9c6560 100644 --- a/core/train/train_resnet18.py +++ b/core/train/train_resnet18.py @@ -2,7 +2,7 @@ import os import torch from core.nets.resnet18 import resnet18 from core.dataloader.dataloader import train_dataloader -from core.const import epoch, lr, batch_size +from core.const import epoch, lr, weight_decay, batch_size def train(): @@ -13,7 +13,7 @@ def train(): loss_func = torch.nn.CrossEntropyLoss() - optimizer = torch.optim.Adam(net.parameters(), lr=lr) + optimizer = torch.optim.Adam(net.parameters(), lr=lr, weight_decay=weight_decay) scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=20, eta_min=1e-6) # 余弦退火 diff --git a/test/001.jpg b/test/001.jpg new file mode 100644 index 0000000..b38bcfa Binary files /dev/null and b/test/001.jpg differ diff --git a/test/002.jpg b/test/002.jpg new file mode 100644 index 0000000..c132eaa Binary files /dev/null and b/test/002.jpg differ diff --git a/test/003.jpg b/test/003.jpg new file mode 100644 index 0000000..4b71742 Binary files /dev/null and b/test/003.jpg differ diff --git a/test/004.jpg b/test/004.jpg new file mode 100644 index 0000000..8df0a17 Binary files /dev/null and b/test/004.jpg differ diff --git a/test/0047.jpg b/test/0047.jpg new file mode 100644 index 0000000..9e51906 Binary files /dev/null and b/test/0047.jpg differ diff --git a/test/005.jpg b/test/005.jpg new file mode 100644 index 0000000..3aac29a Binary files /dev/null and b/test/005.jpg differ diff --git a/test/1988.jpg b/test/1988.jpg new file mode 100644 index 0000000..73170c2 Binary files /dev/null and b/test/1988.jpg differ diff --git a/test/b0099.jpg b/test/b0099.jpg new file mode 100644 index 0000000..a0c0256 Binary files /dev/null and b/test/b0099.jpg differ diff --git a/test/e0021.jpg b/test/e0021.jpg new file mode 100644 index 0000000..56e7e3c Binary files /dev/null and b/test/e0021.jpg differ diff --git a/test/e0071.jpg b/test/e0071.jpg new file mode 100644 index 0000000..4d2be5c Binary files /dev/null and b/test/e0071.jpg differ diff --git a/test/f001.jpg b/test/f001.jpg new file mode 100644 index 0000000..820a3c1 Binary files /dev/null and b/test/f001.jpg differ diff --git a/test/xx001.jpg b/test/xx001.jpg new file mode 100644 index 0000000..adb67a4 Binary files /dev/null and b/test/xx001.jpg differ