fly6516s_Education.test/DeepQuantom-CNN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

train(qccnn): 调整 QCCNN 模型参数并优化训练过程

Browse Source 
-调整早停耐心值和学习率调度器参数
- 移除数据集中的缩放变换- 修正训练集和测试集的加载方式
- 优化 RandomQCCNN 和 QCCNN模型结构
- 调整电路深度和输入形状
- 优化 VGG 模型的全连接层大小
This commit is contained in:
fly6516 2025-06-26 12:02:09 +08:00
parent 9266859f0a
commit cb15dfb430
12 changed files with 394156 additions and 328 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

393999
Modify.ipynb
View File

File diff suppressed because one or more lines are too long

82
Modify.py
View File

@ -71,10 +71,10 @@ def train_model(model, criterion, optimizer, train_loader, valid_loader, num_epo
valid_acc_list = [] valid_acc_list = []
best_valid_acc = 0.0 best_valid_acc = 0.0
patience = 10 # 早停耐心值 patience = 50 # 早停耐心值
counter = 0 # 计数器 counter = 0 # 计数器
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=0.5, patience=10) scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=0.5, patience=25)
with tqdm(total=num_epochs) as pbar: with tqdm(total=num_epochs) as pbar:
for epoch in range(num_epochs): for epoch in range(num_epochs):
@ -170,7 +170,6 @@ trans1 = transforms.Compose([
transforms.RandomHorizontalFlip(), # 随机水平翻转 transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.RandomRotation(10), # 随机旋转±10度 transforms.RandomRotation(10), # 随机旋转±10度
transforms.ColorJitter(brightness=0.2, contrast=0.2), # 颜色调整 transforms.ColorJitter(brightness=0.2, contrast=0.2), # 颜色调整
transforms.Resize((18, 18)), # 调整大小为18x18
transforms.ToTensor(), # 转换为张量 transforms.ToTensor(), # 转换为张量
transforms.Normalize((0.5,), (0.5,)) # 归一化到[-1, 1] transforms.Normalize((0.5,), (0.5,)) # 归一化到[-1, 1]
]) ])
@ -179,11 +178,10 @@ trans2 = transforms.Compose([
transforms.RandomHorizontalFlip(), # 随机水平翻转 transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.RandomRotation(10), # 随机旋转±10度 transforms.RandomRotation(10), # 随机旋转±10度
transforms.ColorJitter(brightness=0.2, contrast=0.2), # 颜色调整 transforms.ColorJitter(brightness=0.2, contrast=0.2), # 颜色调整
transforms.Resize((16, 16)), # 调整大小为16x16
transforms.ToTensor(), # 转换为张量 transforms.ToTensor(), # 转换为张量
transforms.Normalize((0.5,), (0.5,)) # 归一化到[-1, 1] transforms.Normalize((0.5,), (0.5,)) # 归一化到[-1, 1]
]) ])
train_dataset = FashionMNIST(root='./data/notebook2', train=False, transform=trans1,download=True) train_dataset = FashionMNIST(root='./data/notebook2', train=True, transform=trans1,download=True)
test_dataset = FashionMNIST(root='./data/notebook2', train=False, transform=trans1,download=True) test_dataset = FashionMNIST(root='./data/notebook2', train=False, transform=trans1,download=True)
# 定义训练集和测试集的比例 # 定义训练集和测试集的比例
@ -256,26 +254,36 @@ class RandomQCCNN(nn.Module):
def __init__(self): def __init__(self):
super(RandomQCCNN, self).__init__() super(RandomQCCNN, self).__init__()
self.conv = nn.Sequential( self.conv = nn.Sequential(
RandomQuantumConvolutionalLayer(nqubit=4, num_circuits=3, seed=1024), # num_circuits=3代表我们在quanv1层只用了3个量子卷积核 RandomQuantumConvolutionalLayer(nqubit=4, num_circuits=3), # num_circuits=3代表我们在quanv1层只用了3个量子卷积核
nn.BatchNorm2d(3), # 添加批量归一化 nn.BatchNorm2d(3), # 添加批量归一化
nn.ReLU(), nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=1), nn.MaxPool2d(kernel_size=2, stride=1),
# 添加形状检查层以确保尺寸正确
nn.Conv2d(3, 6, kernel_size=2, stride=1), nn.Conv2d(3, 6, kernel_size=2, stride=1),
nn.BatchNorm2d(6), # 添加批量归一化 nn.BatchNorm2d(6), # 添加批量归一化
nn.ReLU(), nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=1) # 添加自适应池化层确保固定输出尺寸
nn.AdaptiveMaxPool2d((9, 9)) # 确保输出固定尺寸
) )
self.fc = nn.Sequential( self.fc = nn.Sequential(
nn.Linear(6 * 6 * 6, 1024), # 根据自适应池化后的固定尺寸计算输入维度
nn.BatchNorm1d(1024), # 添加批量归一化 nn.Linear(6 * 9 * 9, 1024), # 确保与自适应池化输出匹配
nn.Dropout(0.5), # 增加dropout比例 nn.BatchNorm1d(1024),
nn.Dropout(0.5),
nn.ReLU(), nn.ReLU(),
nn.Linear(1024, 10) nn.Linear(1024, 512),
nn.BatchNorm1d(512),
nn.ReLU(),
nn.Linear(512, 10)
) )
def forward(self, x): def forward(self, x):
# 添加详细的形状检查输出
print(f"Input shape: {x.shape}")
x = self.conv(x) x = self.conv(x)
print(f"After conv layers: {x.shape}") # 添加中间形状检查
x = x.reshape(x.size(0), -1) x = x.reshape(x.size(0), -1)
print(f"After flatten: {x.shape}") # 添加展平后形状检查
x = self.fc(x) x = self.fc(x)
return x return x
#%% #%%
@ -335,9 +343,9 @@ class ParameterizedQuantumConvolutionalLayer(nn.Module):
def circuit(self, nqubit): def circuit(self, nqubit):
cir = dq.QubitCircuit(nqubit) cir = dq.QubitCircuit(nqubit)
cir.rxlayer(encode=True) #对原论文的量子线路结构并无影响，只是做了一个数据编码的操作 cir.rxlayer(encode=True) # 数据编码
cir.barrier() cir.barrier()
for iter in range(4): #对应原论文中一个量子卷积线路上的深度为4，可控参数一共16个 for iter in range(5): # 将线路深度从4增加到5
cir.rylayer() cir.rylayer()
cir.cnot_ring() cir.cnot_ring()
cir.barrier() cir.barrier()
@ -346,20 +354,30 @@ class ParameterizedQuantumConvolutionalLayer(nn.Module):
return cir return cir
def forward(self, x): def forward(self, x):
kernel_size, stride = 2, 2 kernel_size, stride = 3, 3 # 使用3x3数据块
# [64, 1, 18, 18] -> [64, 1, 9, 18, 2] -> [64, 1, 9, 9, 2, 2]
x_unflod = x.unfold(2, kernel_size, stride).unfold(3, kernel_size, stride) x_unflod = x.unfold(2, kernel_size, stride).unfold(3, kernel_size, stride)
w = int((x.shape[-1] - kernel_size) / stride + 1) print(f"Input shape: {x.shape}") # 添加输入形状检查
x_reshape = x_unflod.reshape(-1, self.nqubit) print(f"Unfolded shape: {x_unflod.shape}") # 添加展开后形状检查
# 动态计算w值并验证特征图尺寸
w = x_unflod.shape[2] # 使用实际展开后的尺寸
# 确保展平后的总元素数与量子线路输入匹配
x_reshape = x_unflod.reshape(-1, kernel_size * kernel_size) # 将每个3x3块展平为9维
exps = [] exps = []
for cir in self.cirs: # out_channels for cir in self.cirs:
cir(x_reshape) cir(x_reshape)
exp = cir.expectation() exp = cir.expectation()
exps.append(exp) exps.append(exp)
exps = torch.stack(exps, dim=1) exps = torch.stack(exps, dim=1)
exps = exps.reshape(x.shape[0], 3, w, w) out_channels = len(self.cirs) # 使用动态计算而非硬编码值
# 验证总元素数一致性
assert exps.numel() == x.shape[0] * out_channels * w * w, \
f"Element count mismatch: {exps.numel()} vs {x.shape[0] * out_channels * w * w}"
# 确保展平后的总元素数与量子线路输出匹配
exps = exps.reshape(x.shape[0], out_channels, w, w)
print(f"Reshaped shape: {exps.shape}") # 添加最终形状检查
return exps return exps
#%% #%%
# 此处我们可视化其中一个量子卷积核的线路结构： # 此处我们可视化其中一个量子卷积核的线路结构：
@ -371,18 +389,26 @@ class QCCNN(nn.Module):
def __init__(self): def __init__(self):
super(QCCNN, self).__init__() super(QCCNN, self).__init__()
self.conv = nn.Sequential( self.conv = nn.Sequential(
ParameterizedQuantumConvolutionalLayer(nqubit=4, num_circuits=3), ParameterizedQuantumConvolutionalLayer(nqubit=4, num_circuits=3), # 恢复为4量子比特
nn.BatchNorm2d(3), # 添加批量归一化 nn.BatchNorm2d(3), # 恢复原始通道数
nn.ReLU(), nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=1) nn.MaxPool2d(kernel_size=2, stride=1),
nn.Conv2d(3, 6, kernel_size=1), # 添加1x1卷积层增强通道间信息交互
nn.BatchNorm2d(6),
nn.ReLU(),
nn.AdaptiveMaxPool2d((9, 9)) # 确保输出固定尺寸
) )
self.fc = nn.Sequential( self.fc = nn.Sequential(
nn.Linear(8 * 8 * 3, 128), # 根据新的特征图大小调整输入维度：6通道、9x9特征图 => 6*9*9=486
nn.BatchNorm1d(128), # 添加批量归一化 nn.Linear(6 * 9 * 9, 1024), # 修改为正确的输入维度
nn.Dropout(0.5), # 增加dropout比例 nn.BatchNorm1d(1024),
nn.Dropout(0.5),
nn.ReLU(), nn.ReLU(),
nn.Linear(128, 10) nn.Linear(1024, 512),
nn.BatchNorm1d(512),
nn.ReLU(),
nn.Linear(512, 10)
) )
def forward(self, x): def forward(self, x):
@ -398,7 +424,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = QCCNN() model = QCCNN()
model.to(device) model.to(device)
criterion = nn.CrossEntropyLoss() criterion = nn.CrossEntropyLoss()
optimizer = optim.AdamW(model.parameters(), lr=3e-4, weight_decay=1e-5) # 使用AdamW优化器和适当的权重衰减 optimizer = optim.AdamW(model.parameters(), lr=5e-4, weight_decay=5e-5, amsgrad=True) # 优化学习率和weight_decay参数
optim_model, metrics = train_model(model, criterion, optimizer, train_loader, valid_loader, num_epochs, device) optim_model, metrics = train_model(model, criterion, optimizer, train_loader, valid_loader, num_epochs, device)
torch.save(optim_model.state_dict(), './data/notebook2/qccnn_weights.pt') # 保存训练好的模型参数，用于后续的推理或测试 torch.save(optim_model.state_dict(), './data/notebook2/qccnn_weights.pt') # 保存训练好的模型参数，用于后续的推理或测试
pd.DataFrame(metrics).to_csv('./data/notebook2/qccnn_metrics.csv', index='None') # 保存模型训练过程，用于后续图标展示 pd.DataFrame(metrics).to_csv('./data/notebook2/qccnn_metrics.csv', index='None') # 保存模型训练过程，用于后续图标展示
@ -425,7 +451,7 @@ VGG = nn.Sequential(
vgg_block(1, 32, 2), # 增加通道数和调整卷积层数量 vgg_block(1, 32, 2), # 增加通道数和调整卷积层数量
vgg_block(32, 64, 2), vgg_block(32, 64, 2),
nn.Flatten(), nn.Flatten(),
nn.Linear(64 * 4 * 4, 256), # 调整全连接层大小 nn.Linear(64 * 7 * 7, 256), # 修改为正确的输入维度
nn.BatchNorm1d(256), # 添加批量归一化 nn.BatchNorm1d(256), # 添加批量归一化
nn.ReLU(), nn.ReLU(),
nn.Dropout(0.5), # 增加dropout比例 nn.Dropout(0.5), # 增加dropout比例

BIN
data/notebook2/best_model.pt
View File

Binary file not shown.

BIN
data/notebook2/qccnn_best.pt
View File

Binary file not shown.

108
data/notebook2/qccnn_metrics.csv
View File

@ -1,49 +1,61 @@
,epoch,train_acc,valid_acc,train_loss,valid_loss ,epoch,train_acc,valid_acc,train_loss,valid_loss
0,1,0.391375,0.5882056451612904,1.7793689422607422,1.3356874796652025 0,1,0.6956875,0.7605280748663101,0.8211820412079494,0.6387985139925849
1,2,0.617125,0.6365927419354839,1.059556163787842,0.9690603344671188 1,2,0.7645416666666667,0.787850935828877,0.6182981830437978,0.5789241027385793
2,3,0.663125,0.6577620967741935,0.9102170023918151,0.9078671547674364 2,3,0.7837916666666667,0.7884358288770054,0.5628398391008377,0.5625918760975415
3,4,0.69,0.6819556451612904,0.8537670917510987,0.8649420180628377 3,4,0.7983958333333333,0.8048128342245989,0.5307413680950801,0.5154492698888727
4,5,0.71125,0.7056451612903226,0.8021836678981781,0.8317571128568342 4,5,0.8067291666666667,0.8016377005347594,0.5082246935367585,0.5231997628900457
5,6,0.719375,0.6844758064516129,0.7773117737770081,0.8293971457789021 5,6,0.812,0.8068181818181818,0.48933065092563627,0.516960185957465
6,7,0.733,0.7247983870967742,0.7432277894020081,0.7570091389840649 6,7,0.8195416666666666,0.8124164438502673,0.47495536905527114,0.4998339513406397
7,8,0.727125,0.7051411290322581,0.7392586808204651,0.7708722833664187 7,8,0.8227708333333333,0.8236965240641712,0.46346363043785094,0.4768249858668781
8,9,0.740375,0.7091733870967742,0.716008551120758,0.7547545788749572 8,9,0.8255625,0.8194351604278075,0.45567453374465305,0.4821742607310494
9,10,0.74775,0.7091733870967742,0.6988923935890198,0.7634256799374858 9,10,0.8315,0.825701871657754,0.44574370459715523,0.46175671978430316
10,11,0.75025,0.7328629032258065,0.6836859595775604,0.7220065324537216 10,11,0.8308125,0.8133355614973262,0.4422872595389684,0.4978986528308634
11,12,0.75525,0.7313508064516129,0.6790840411186219,0.7320531125991575 11,12,0.8348125,0.8301303475935828,0.4311412891546885,0.4576163932601398
12,13,0.755875,0.734375,0.6686462206840516,0.7067360877990723 12,13,0.8376041666666667,0.8193516042780749,0.42240108201901116,0.4770477739247409
13,14,0.755875,0.7338709677419355,0.659578008890152,0.6924379564100697 13,14,0.8385625,0.8282921122994652,0.418784587085247,0.4626272647457327
14,15,0.758625,0.7217741935483871,0.6591809678077698,0.7092515037905786 14,15,0.8436041666666667,0.8350601604278075,0.41075574096043904,0.44758253596364495
15,16,0.770125,0.7474798387096774,0.6366513178348542,0.6689942498360911 15,16,0.8421875,0.8313001336898396,0.4109448278148969,0.446757927218223
16,17,0.76975,0.75,0.64143789935112,0.6781372427940369 16,17,0.8435625,0.8346423796791443,0.40630192184448244,0.4484061913534919
17,18,0.766625,0.7469758064516129,0.6327295961380005,0.6749444469328849 17,18,0.8458541666666667,0.8385695187165776,0.40021699021259943,0.4367518940552033
18,19,0.772125,0.7298387096774194,0.6213552060127259,0.6950428524324971 18,19,0.847125,0.8307152406417112,0.3976554674903552,0.44405238075371095
19,20,0.771625,0.7560483870967742,0.619529750585556,0.6620656597998834 19,20,0.8483125,0.8386530748663101,0.3941614780028661,0.4367401426169962
20,21,0.77425,0.7459677419354839,0.6170263500213623,0.6944894117693747 20,21,0.8502916666666667,0.8384024064171123,0.3900964806675911,0.4330310898031143
21,22,0.77375,0.7379032258064516,0.610548350572586,0.698592597438443 21,22,0.850875,0.8379010695187166,0.38837515221039454,0.43586291532146737
22,23,0.774125,0.7494959677419355,0.6073116481304168,0.6649176555295144 22,23,0.8517291666666666,0.8390708556149733,0.3842192193667094,0.43854525677341827
23,24,0.78,0.75,0.601892656326294,0.6502023070089279 23,24,0.8533958333333334,0.8319685828877005,0.37822781956195833,0.43952455710281024
24,25,0.777875,0.7671370967741935,0.5965238115787506,0.6416350141648324 24,25,0.8521041666666667,0.8424966577540107,0.38170819969971975,0.42412006687671744
25,26,0.7875,0.751008064516129,0.584319313287735,0.6557927843063108 25,26,0.8566875,0.8418282085561497,0.3745041756629944,0.42809357434351814
26,27,0.784625,0.7651209677419355,0.5858220131397247,0.6265111680953733 26,27,0.8584583333333333,0.8440842245989305,0.3699158744017283,0.4245206856313236
27,28,0.77975,0.7610887096774194,0.5928270950317382,0.6353864400617538 27,28,0.8557708333333334,0.841995320855615,0.37092407973607383,0.422711970892182
28,29,0.780625,0.7520161290322581,0.5824392430782318,0.6569667564284417 28,29,0.8590625,0.8429979946524064,0.36935959541797636,0.42758023595427447
29,30,0.78475,0.7686491935483871,0.5810435285568237,0.6306867743692091 29,30,0.8596041666666666,0.8488469251336899,0.3606020367145538,0.4196776971619397
30,31,0.789,0.7706653225806451,0.5672282783985138,0.6261125274242894 30,31,0.8629166666666667,0.8481784759358288,0.3595893513560295,0.41790072508355514
31,32,0.78525,0.7560483870967742,0.5757509377002716,0.6505500414679127 31,32,0.8611875,0.8426637700534759,0.3579425945480665,0.42967644118688963
32,33,0.792,0.7681451612903226,0.5613697295188904,0.629849144527989 32,33,0.8640416666666667,0.8465909090909091,0.3525094211200873,0.41836620102272953
33,34,0.793875,0.7620967741935484,0.5625830183029175,0.6189906856706066 33,34,0.8626875,0.8418282085561497,0.3546509333451589,0.4231800782011155
34,35,0.791875,0.7681451612903226,0.5602230775356293,0.6212261732547514 34,35,0.8648333333333333,0.8489304812834224,0.3503157667120298,0.4183035452257503
35,36,0.794625,0.7615927419354839,0.5545250961780548,0.619811047469416 35,36,0.8643958333333334,0.8440006684491979,0.3498730379541715,0.4190998378603216
36,37,0.794625,0.7701612903225806,0.5573954427242279,0.6205428954093687 36,37,0.87175,0.8534425133689839,0.32715407966574034,0.4019120936406487
37,38,0.79425,0.764616935483871,0.5514744529724122,0.628905875067557 37,38,0.8728541666666667,0.8485127005347594,0.32552256182829536,0.4089040935517632
38,39,0.792375,0.7842741935483871,0.5618353080749512,0.5954909113145643 38,39,0.876375,0.852105614973262,0.32196691662073135,0.40356063794962227
39,40,0.796375,0.7711693548387096,0.5491654114723206,0.6137347759739045 39,40,0.8771875,0.85235628342246,0.31610893772045773,0.4059840437562708
40,41,0.799,0.7641129032258065,0.5372960684299469,0.6470560056547965 40,41,0.8779583333333333,0.8501002673796791,0.3148737497230371,0.40458757402425144
41,42,0.800375,0.7671370967741935,0.5395989503860473,0.6211921880322118 41,42,0.8783541666666667,0.8511029411764706,0.31425037946303686,0.40025874677507634
42,43,0.806,0.7671370967741935,0.5370515692234039,0.6075864828401997 42,43,0.879125,0.8485127005347594,0.31071714136004447,0.41301197538720097
43,44,0.801875,0.7605846774193549,0.5388010408878326,0.5891174308715328 43,44,0.8840833333333333,0.8587065508021391,0.297863828599453,0.38672817749454375
44,45,0.800875,0.766633064516129,0.539761929512024,0.610026998865989 44,45,0.8851875,0.8551136363636364,0.29304139083623887,0.3945167065463602
45,46,0.802375,0.780241935483871,0.5270701496601105,0.6000283591208919 45,46,0.8866666666666667,0.8526069518716578,0.2949504310488701,0.4007673603009413
46,47,0.799875,0.7772177419354839,0.5320828959941865,0.5864833074231302 46,47,0.887875,0.8566176470588235,0.2923740311563015,0.39658332620075043
47,48,0.807,0.7837701612903226,0.5309389193058014,0.5761975809451072 47,48,0.8865625,0.8573696524064172,0.29297807250420255,0.39060447871047543
48,49,0.8876458333333334,0.8531918449197861,0.29198914767305056,0.4017815204227672
49,50,0.8903125,0.8556985294117647,0.28550282220045725,0.3990818190383401
50,51,0.8921041666666667,0.8613803475935828,0.2811181089083354,0.38583621303027965
51,52,0.8912708333333333,0.8602941176470589,0.2825057551066081,0.38899426345519206
52,53,0.8914375,0.8542780748663101,0.28124154203136764,0.4000103534224199
53,54,0.8925416666666667,0.8579545454545454,0.2816228237350782,0.39209578182289306
54,55,0.8924375,0.8584558823529411,0.2785300021370252,0.38789646502803354
55,56,0.8932083333333334,0.8587065508021391,0.27603148049116133,0.39326987443442013
56,57,0.8931458333333333,0.8557820855614974,0.27797147376338643,0.4011580384670094
57,58,0.8956875,0.8595421122994652,0.2708657040695349,0.3850319666817864
58,59,0.8921458333333333,0.8613803475935828,0.274147473325332,0.3814745011495396
59,60,0.8947291666666667,0.8602941176470589,0.2712443074285984,0.39393253767872877

1 epoch train_acc valid_acc train_loss valid_loss
2 0 1 0.391375 0.6956875 0.5882056451612904 0.7605280748663101 1.7793689422607422 0.8211820412079494 1.3356874796652025 0.6387985139925849
3 1 2 0.617125 0.7645416666666667 0.6365927419354839 0.787850935828877 1.059556163787842 0.6182981830437978 0.9690603344671188 0.5789241027385793
4 2 3 0.663125 0.7837916666666667 0.6577620967741935 0.7884358288770054 0.9102170023918151 0.5628398391008377 0.9078671547674364 0.5625918760975415
5 3 4 0.69 0.7983958333333333 0.6819556451612904 0.8048128342245989 0.8537670917510987 0.5307413680950801 0.8649420180628377 0.5154492698888727
6 4 5 0.71125 0.8067291666666667 0.7056451612903226 0.8016377005347594 0.8021836678981781 0.5082246935367585 0.8317571128568342 0.5231997628900457
7 5 6 0.719375 0.812 0.6844758064516129 0.8068181818181818 0.7773117737770081 0.48933065092563627 0.8293971457789021 0.516960185957465
8 6 7 0.733 0.8195416666666666 0.7247983870967742 0.8124164438502673 0.7432277894020081 0.47495536905527114 0.7570091389840649 0.4998339513406397
9 7 8 0.727125 0.8227708333333333 0.7051411290322581 0.8236965240641712 0.7392586808204651 0.46346363043785094 0.7708722833664187 0.4768249858668781
10 8 9 0.740375 0.8255625 0.7091733870967742 0.8194351604278075 0.716008551120758 0.45567453374465305 0.7547545788749572 0.4821742607310494
11 9 10 0.74775 0.8315 0.7091733870967742 0.825701871657754 0.6988923935890198 0.44574370459715523 0.7634256799374858 0.46175671978430316
12 10 11 0.75025 0.8308125 0.7328629032258065 0.8133355614973262 0.6836859595775604 0.4422872595389684 0.7220065324537216 0.4978986528308634
13 11 12 0.75525 0.8348125 0.7313508064516129 0.8301303475935828 0.6790840411186219 0.4311412891546885 0.7320531125991575 0.4576163932601398
14 12 13 0.755875 0.8376041666666667 0.734375 0.8193516042780749 0.6686462206840516 0.42240108201901116 0.7067360877990723 0.4770477739247409
15 13 14 0.755875 0.8385625 0.7338709677419355 0.8282921122994652 0.659578008890152 0.418784587085247 0.6924379564100697 0.4626272647457327
16 14 15 0.758625 0.8436041666666667 0.7217741935483871 0.8350601604278075 0.6591809678077698 0.41075574096043904 0.7092515037905786 0.44758253596364495
17 15 16 0.770125 0.8421875 0.7474798387096774 0.8313001336898396 0.6366513178348542 0.4109448278148969 0.6689942498360911 0.446757927218223
18 16 17 0.76975 0.8435625 0.75 0.8346423796791443 0.64143789935112 0.40630192184448244 0.6781372427940369 0.4484061913534919
19 17 18 0.766625 0.8458541666666667 0.7469758064516129 0.8385695187165776 0.6327295961380005 0.40021699021259943 0.6749444469328849 0.4367518940552033
20 18 19 0.772125 0.847125 0.7298387096774194 0.8307152406417112 0.6213552060127259 0.3976554674903552 0.6950428524324971 0.44405238075371095
21 19 20 0.771625 0.8483125 0.7560483870967742 0.8386530748663101 0.619529750585556 0.3941614780028661 0.6620656597998834 0.4367401426169962
22 20 21 0.77425 0.8502916666666667 0.7459677419354839 0.8384024064171123 0.6170263500213623 0.3900964806675911 0.6944894117693747 0.4330310898031143
23 21 22 0.77375 0.850875 0.7379032258064516 0.8379010695187166 0.610548350572586 0.38837515221039454 0.698592597438443 0.43586291532146737
24 22 23 0.774125 0.8517291666666666 0.7494959677419355 0.8390708556149733 0.6073116481304168 0.3842192193667094 0.6649176555295144 0.43854525677341827
25 23 24 0.78 0.8533958333333334 0.75 0.8319685828877005 0.601892656326294 0.37822781956195833 0.6502023070089279 0.43952455710281024
26 24 25 0.777875 0.8521041666666667 0.7671370967741935 0.8424966577540107 0.5965238115787506 0.38170819969971975 0.6416350141648324 0.42412006687671744
27 25 26 0.7875 0.8566875 0.751008064516129 0.8418282085561497 0.584319313287735 0.3745041756629944 0.6557927843063108 0.42809357434351814
28 26 27 0.784625 0.8584583333333333 0.7651209677419355 0.8440842245989305 0.5858220131397247 0.3699158744017283 0.6265111680953733 0.4245206856313236
29 27 28 0.77975 0.8557708333333334 0.7610887096774194 0.841995320855615 0.5928270950317382 0.37092407973607383 0.6353864400617538 0.422711970892182
30 28 29 0.780625 0.8590625 0.7520161290322581 0.8429979946524064 0.5824392430782318 0.36935959541797636 0.6569667564284417 0.42758023595427447
31 29 30 0.78475 0.8596041666666666 0.7686491935483871 0.8488469251336899 0.5810435285568237 0.3606020367145538 0.6306867743692091 0.4196776971619397
32 30 31 0.789 0.8629166666666667 0.7706653225806451 0.8481784759358288 0.5672282783985138 0.3595893513560295 0.6261125274242894 0.41790072508355514
33 31 32 0.78525 0.8611875 0.7560483870967742 0.8426637700534759 0.5757509377002716 0.3579425945480665 0.6505500414679127 0.42967644118688963
34 32 33 0.792 0.8640416666666667 0.7681451612903226 0.8465909090909091 0.5613697295188904 0.3525094211200873 0.629849144527989 0.41836620102272953
35 33 34 0.793875 0.8626875 0.7620967741935484 0.8418282085561497 0.5625830183029175 0.3546509333451589 0.6189906856706066 0.4231800782011155
36 34 35 0.791875 0.8648333333333333 0.7681451612903226 0.8489304812834224 0.5602230775356293 0.3503157667120298 0.6212261732547514 0.4183035452257503
37 35 36 0.794625 0.8643958333333334 0.7615927419354839 0.8440006684491979 0.5545250961780548 0.3498730379541715 0.619811047469416 0.4190998378603216
38 36 37 0.794625 0.87175 0.7701612903225806 0.8534425133689839 0.5573954427242279 0.32715407966574034 0.6205428954093687 0.4019120936406487
39 37 38 0.79425 0.8728541666666667 0.764616935483871 0.8485127005347594 0.5514744529724122 0.32552256182829536 0.628905875067557 0.4089040935517632
40 38 39 0.792375 0.876375 0.7842741935483871 0.852105614973262 0.5618353080749512 0.32196691662073135 0.5954909113145643 0.40356063794962227
41 39 40 0.796375 0.8771875 0.7711693548387096 0.85235628342246 0.5491654114723206 0.31610893772045773 0.6137347759739045 0.4059840437562708
42 40 41 0.799 0.8779583333333333 0.7641129032258065 0.8501002673796791 0.5372960684299469 0.3148737497230371 0.6470560056547965 0.40458757402425144
43 41 42 0.800375 0.8783541666666667 0.7671370967741935 0.8511029411764706 0.5395989503860473 0.31425037946303686 0.6211921880322118 0.40025874677507634
44 42 43 0.806 0.879125 0.7671370967741935 0.8485127005347594 0.5370515692234039 0.31071714136004447 0.6075864828401997 0.41301197538720097
45 43 44 0.801875 0.8840833333333333 0.7605846774193549 0.8587065508021391 0.5388010408878326 0.297863828599453 0.5891174308715328 0.38672817749454375
46 44 45 0.800875 0.8851875 0.766633064516129 0.8551136363636364 0.539761929512024 0.29304139083623887 0.610026998865989 0.3945167065463602
47 45 46 0.802375 0.8866666666666667 0.780241935483871 0.8526069518716578 0.5270701496601105 0.2949504310488701 0.6000283591208919 0.4007673603009413
48 46 47 0.799875 0.887875 0.7772177419354839 0.8566176470588235 0.5320828959941865 0.2923740311563015 0.5864833074231302 0.39658332620075043
49 47 48 0.807 0.8865625 0.7837701612903226 0.8573696524064172 0.5309389193058014 0.29297807250420255 0.5761975809451072 0.39060447871047543
50 48 49 0.8876458333333334 0.8531918449197861 0.29198914767305056 0.4017815204227672
51 49 50 0.8903125 0.8556985294117647 0.28550282220045725 0.3990818190383401
52 50 51 0.8921041666666667 0.8613803475935828 0.2811181089083354 0.38583621303027965
53 51 52 0.8912708333333333 0.8602941176470589 0.2825057551066081 0.38899426345519206
54 52 53 0.8914375 0.8542780748663101 0.28124154203136764 0.4000103534224199
55 53 54 0.8925416666666667 0.8579545454545454 0.2816228237350782 0.39209578182289306
56 54 55 0.8924375 0.8584558823529411 0.2785300021370252 0.38789646502803354
57 55 56 0.8932083333333334 0.8587065508021391 0.27603148049116133 0.39326987443442013
58 56 57 0.8931458333333333 0.8557820855614974 0.27797147376338643 0.4011580384670094
59 57 58 0.8956875 0.8595421122994652 0.2708657040695349 0.3850319666817864
60 58 59 0.8921458333333333 0.8613803475935828 0.274147473325332 0.3814745011495396
61 59 60 0.8947291666666667 0.8602941176470589 0.2712443074285984 0.39393253767872877

BIN
data/notebook2/qccnn_weights.pt
View File

Binary file not shown.

BIN
data/notebook2/random_qccnn_best.pt
View File

Binary file not shown.

110
data/notebook2/random_qccnn_metrics.csv
View File

@ -1,34 +1,78 @@
,epoch,train_acc,valid_acc,train_loss,valid_loss ,epoch,train_acc,valid_acc,train_loss,valid_loss
0,1,0.561125,0.6476814516129032,1.271985122203827,0.9911825291572078 0,1,0.6058333333333333,0.7088068181818182,1.077100011587143,0.7878920158600424
1,2,0.676375,0.6668346774193549,0.9134431419372558,0.8937955517922679 1,2,0.7224166666666667,0.7269385026737968,0.7470338317950567,0.7390924543939172
2,3,0.699125,0.6824596774193549,0.8243759956359863,0.8520721235582905 2,3,0.7520208333333334,0.7539271390374331,0.6676628764470418,0.6713398865518723
3,4,0.716625,0.6995967741935484,0.7818560593128204,0.8005917687569896 3,4,0.7725208333333333,0.7676303475935828,0.612583932240804,0.6310215724662026
4,5,0.725125,0.7101814516129032,0.745261854171753,0.8037946531849522 4,5,0.7787916666666667,0.7807486631016043,0.5905240491827329,0.594515474244235
5,6,0.733375,0.7061491935483871,0.7344184167385102,0.7732808570707997 5,6,0.7867083333333333,0.7794117647058824,0.568865264693896,0.5900490468836086
6,7,0.737875,0.7253024193548387,0.7150477197170257,0.74149090051651 6,7,0.7952708333333334,0.7901069518716578,0.5486233344872793,0.553959414283222
7,8,0.74325,0.7253024193548387,0.7022454526424408,0.7516527022084882 7,8,0.7990416666666667,0.7973763368983957,0.5307548115452131,0.5483398674962355
8,9,0.742625,0.7298387096774194,0.7041031284332275,0.7247120468847214 8,9,0.8028958333333334,0.7942847593582888,0.5225638653437297,0.553332871613018
9,10,0.747875,0.7116935483870968,0.6772661633491516,0.7338270487323884 9,10,0.808875,0.7990474598930482,0.5071384527683258,0.5478345090373952
10,11,0.757875,0.7212701612903226,0.6562292041778565,0.7387931039256435 10,11,0.8109166666666666,0.8043114973262032,0.49932783031463623,0.5302995911893997
11,12,0.761625,0.7328629032258065,0.6542983632087708,0.725050816612859 11,12,0.8152083333333333,0.7998830213903744,0.4876467382510503,0.5369620672203003
12,13,0.75925,0.7318548387096774,0.6493379819393158,0.7001086867624714 12,13,0.8218333333333333,0.8055648395721925,0.47221228990952174,0.5228660841357899
13,14,0.767375,0.7379032258064516,0.6460576868057251,0.6988139988914612 13,14,0.818875,0.8045621657754011,0.47462575109799704,0.5175498661829189
14,15,0.765875,0.7288306451612904,0.6339491362571716,0.7128441218406923 14,15,0.8245625,0.8102439839572193,0.46200620504220324,0.5206660962997274
15,16,0.763125,0.7368951612903226,0.6262373595237732,0.714297366719092 15,16,0.8271875,0.817346256684492,0.4543743284543355,0.4972638836837707
16,17,0.76925,0.7227822580645161,0.6279029569625855,0.7181522269402781 16,17,0.8277916666666667,0.8086564171122995,0.45034414579470955,0.5051890009227283
17,18,0.77025,0.7449596774193549,0.6159816448688507,0.6757595616002237 17,18,0.827625,0.8130848930481284,0.445495897213618,0.5063204698384127
18,19,0.7745,0.7283266129032258,0.6136245548725128,0.6998546681096477 18,19,0.8327291666666666,0.8187667112299465,0.4373013471563657,0.49322714222306235
19,20,0.775375,0.7469758064516129,0.6000997524261474,0.6749713065162781 19,20,0.835875,0.8227774064171123,0.428063592116038,0.48620352627121827
20,21,0.7805,0.748991935483871,0.5928600332736969,0.6656959902855658 20,21,0.8376875,0.825701871657754,0.42721951069434483,0.4824375149241106
21,22,0.77525,0.7444556451612904,0.599046837568283,0.6857193170055267 21,22,0.8393333333333334,0.8237800802139037,0.424452906926473,0.47128429227971774
22,23,0.785,0.7384072580645161,0.5875316572189331,0.6785462142959717 22,23,0.8394791666666667,0.8235294117647058,0.4193731239239375,0.4921083778621041
23,24,0.778375,0.765625,0.588378502368927,0.627939272311426 23,24,0.8411041666666667,0.8219418449197861,0.4158371254205704,0.4766464689995516
24,25,0.78575,0.7459677419354839,0.5700427904129028,0.6502643679418871 24,25,0.8403958333333333,0.8226102941176471,0.4133129887978236,0.4774917462133469
25,26,0.7805,0.75,0.5785817315578461,0.6712307555060233 25,26,0.8443541666666666,0.8231116310160428,0.40567960069576897,0.48197355627376126
26,27,0.78675,0.7474798387096774,0.5676946561336518,0.6555941143343526 26,27,0.8448958333333333,0.8270387700534759,0.4060484048128128,0.48230106714256304
27,28,0.787875,0.7505040322580645,0.575938116312027,0.6507430134281036 27,28,0.8460625,0.8224431818181818,0.403180761963129,0.48200917403328225
28,29,0.789,0.7605846774193549,0.5655779435634612,0.6520830373610219 28,29,0.8495416666666666,0.8254512032085561,0.39154566899935406,0.4732334581925907
29,30,0.790625,0.7434475806451613,0.5578647639751434,0.6789213486256138 29,30,0.849375,0.8205213903743316,0.3910754985809326,0.5025412492095468
30,31,0.787375,0.7565524193548387,0.5687701859474182,0.649224087115257 30,31,0.850125,0.8200200534759359,0.3879919012586276,0.48824962750475676
31,32,0.79575,0.7560483870967742,0.5432633152008056,0.6388471222692921 31,32,0.8501666666666666,0.8283756684491979,0.3852265829642614,0.4738096959769407
32,33,0.7895,0.7595766129032258,0.5557173223495483,0.6391933618053314 32,33,0.8533125,0.8280414438502673,0.3842975225051244,0.480888257131857
33,34,0.8546666666666667,0.8279578877005348,0.3802658775647481,0.4736704102015113
34,35,0.8553541666666666,0.8287934491978609,0.37693077965577443,0.47027840429448825
35,36,0.8574583333333333,0.8280414438502673,0.37416908142964045,0.47105003949155144
36,37,0.8575416666666666,0.8333890374331551,0.370725477874279,0.4729995278113666
37,38,0.8593333333333333,0.8318850267379679,0.3660616307258606,0.46004778090964027
38,39,0.86125,0.8230280748663101,0.36278441416223844,0.4792340671155542
39,40,0.8597291666666667,0.8328877005347594,0.36306345409154894,0.4713420571490405
40,41,0.8594583333333333,0.8338903743315508,0.35881871738036475,0.457705247131261
41,42,0.86125,0.8338903743315508,0.35548474109172823,0.4744296157583196
42,43,0.8638958333333333,0.8328877005347594,0.35729147561391195,0.46916984149160235
43,44,0.864375,0.8360628342245989,0.3560072028040886,0.45340159527439483
44,45,0.8649791666666666,0.829879679144385,0.35113127034902575,0.4705522551256068
45,46,0.8642708333333333,0.832302807486631,0.3466692521572113,0.4682676112428706
46,47,0.8671458333333333,0.8295454545454546,0.34586968237161636,0.4741511169601889
47,48,0.867125,0.8333890374331551,0.3455539164741834,0.47975461392160407
48,49,0.8672916666666667,0.8318014705882353,0.34170353756348293,0.4724194825811182
49,50,0.8685416666666667,0.830548128342246,0.33824845480918886,0.47551511706196686
50,51,0.8786875,0.8408255347593583,0.31427997442086536,0.45161250855195967
51,52,0.8811666666666667,0.8393215240641712,0.3106038907766342,0.45226032346646416
52,53,0.881875,0.8417446524064172,0.3050905155738195,0.44453552421082787
53,54,0.8818958333333333,0.8420788770053476,0.30438282175858816,0.45232303249325984
54,55,0.8853958333333334,0.8393215240641712,0.29754234209656716,0.45854009632120796
55,56,0.8851041666666667,0.8404913101604278,0.29953089368343355,0.4524733354063595
56,57,0.8845625,0.8411597593582888,0.29662314279874163,0.45404982789952486
57,58,0.8874166666666666,0.8431651069518716,0.29427229724327725,0.45166250935850294
58,59,0.8859375,0.8394050802139037,0.29326443988084794,0.46354111527057895
59,60,0.888375,0.8429979946524064,0.2878838664491971,0.4655548495086119
60,61,0.8886666666666667,0.8424966577540107,0.2877097588280837,0.45055208335267033
61,62,0.889125,0.8429144385026738,0.2842213006118933,0.4635044741917421
62,63,0.8885625,0.8435828877005348,0.2865720265607039,0.4594836203172245
63,64,0.8917708333333333,0.8379010695187166,0.285613534172376,0.4660476203111404
64,65,0.8910625,0.8383188502673797,0.28201638598243395,0.4701039531332924
65,66,0.8908958333333333,0.8407419786096256,0.2792068747878075,0.47005820457629344
66,67,0.8923333333333333,0.8440006684491979,0.2773614428540071,0.4646621039685081
67,68,0.8912291666666666,0.8459224598930482,0.28061300626397134,0.45556305787142587
68,69,0.8947083333333333,0.8403241978609626,0.27382597197095554,0.4730077214578894
69,70,0.8913958333333334,0.8402406417112299,0.2796522062718868,0.4642943452226924
70,71,0.8939375,0.8412433155080213,0.27323526923855146,0.4593185937022143
71,72,0.8947708333333333,0.841326871657754,0.2720908187329769,0.4730970057892927
72,73,0.8960208333333334,0.8417446524064172,0.26792943899333477,0.47570018247168333
73,74,0.8949791666666667,0.8415775401069518,0.27027500013510386,0.4757912041828594
74,75,0.9015208333333333,0.8446691176470589,0.257486442198356,0.4704125145858622
75,76,0.9023333333333333,0.8451704545454546,0.25169081447521846,0.46167185049962234
76,77,0.9014583333333334,0.8432486631016043,0.2498825814574957,0.462763199672342

1 epoch train_acc valid_acc train_loss valid_loss
2 0 1 0.561125 0.6058333333333333 0.6476814516129032 0.7088068181818182 1.271985122203827 1.077100011587143 0.9911825291572078 0.7878920158600424
3 1 2 0.676375 0.7224166666666667 0.6668346774193549 0.7269385026737968 0.9134431419372558 0.7470338317950567 0.8937955517922679 0.7390924543939172
4 2 3 0.699125 0.7520208333333334 0.6824596774193549 0.7539271390374331 0.8243759956359863 0.6676628764470418 0.8520721235582905 0.6713398865518723
5 3 4 0.716625 0.7725208333333333 0.6995967741935484 0.7676303475935828 0.7818560593128204 0.612583932240804 0.8005917687569896 0.6310215724662026
6 4 5 0.725125 0.7787916666666667 0.7101814516129032 0.7807486631016043 0.745261854171753 0.5905240491827329 0.8037946531849522 0.594515474244235
7 5 6 0.733375 0.7867083333333333 0.7061491935483871 0.7794117647058824 0.7344184167385102 0.568865264693896 0.7732808570707997 0.5900490468836086
8 6 7 0.737875 0.7952708333333334 0.7253024193548387 0.7901069518716578 0.7150477197170257 0.5486233344872793 0.74149090051651 0.553959414283222
9 7 8 0.74325 0.7990416666666667 0.7253024193548387 0.7973763368983957 0.7022454526424408 0.5307548115452131 0.7516527022084882 0.5483398674962355
10 8 9 0.742625 0.8028958333333334 0.7298387096774194 0.7942847593582888 0.7041031284332275 0.5225638653437297 0.7247120468847214 0.553332871613018
11 9 10 0.747875 0.808875 0.7116935483870968 0.7990474598930482 0.6772661633491516 0.5071384527683258 0.7338270487323884 0.5478345090373952
12 10 11 0.757875 0.8109166666666666 0.7212701612903226 0.8043114973262032 0.6562292041778565 0.49932783031463623 0.7387931039256435 0.5302995911893997
13 11 12 0.761625 0.8152083333333333 0.7328629032258065 0.7998830213903744 0.6542983632087708 0.4876467382510503 0.725050816612859 0.5369620672203003
14 12 13 0.75925 0.8218333333333333 0.7318548387096774 0.8055648395721925 0.6493379819393158 0.47221228990952174 0.7001086867624714 0.5228660841357899
15 13 14 0.767375 0.818875 0.7379032258064516 0.8045621657754011 0.6460576868057251 0.47462575109799704 0.6988139988914612 0.5175498661829189
16 14 15 0.765875 0.8245625 0.7288306451612904 0.8102439839572193 0.6339491362571716 0.46200620504220324 0.7128441218406923 0.5206660962997274
17 15 16 0.763125 0.8271875 0.7368951612903226 0.817346256684492 0.6262373595237732 0.4543743284543355 0.714297366719092 0.4972638836837707
18 16 17 0.76925 0.8277916666666667 0.7227822580645161 0.8086564171122995 0.6279029569625855 0.45034414579470955 0.7181522269402781 0.5051890009227283
19 17 18 0.77025 0.827625 0.7449596774193549 0.8130848930481284 0.6159816448688507 0.445495897213618 0.6757595616002237 0.5063204698384127
20 18 19 0.7745 0.8327291666666666 0.7283266129032258 0.8187667112299465 0.6136245548725128 0.4373013471563657 0.6998546681096477 0.49322714222306235
21 19 20 0.775375 0.835875 0.7469758064516129 0.8227774064171123 0.6000997524261474 0.428063592116038 0.6749713065162781 0.48620352627121827
22 20 21 0.7805 0.8376875 0.748991935483871 0.825701871657754 0.5928600332736969 0.42721951069434483 0.6656959902855658 0.4824375149241106
23 21 22 0.77525 0.8393333333333334 0.7444556451612904 0.8237800802139037 0.599046837568283 0.424452906926473 0.6857193170055267 0.47128429227971774
24 22 23 0.785 0.8394791666666667 0.7384072580645161 0.8235294117647058 0.5875316572189331 0.4193731239239375 0.6785462142959717 0.4921083778621041
25 23 24 0.778375 0.8411041666666667 0.765625 0.8219418449197861 0.588378502368927 0.4158371254205704 0.627939272311426 0.4766464689995516
26 24 25 0.78575 0.8403958333333333 0.7459677419354839 0.8226102941176471 0.5700427904129028 0.4133129887978236 0.6502643679418871 0.4774917462133469
27 25 26 0.7805 0.8443541666666666 0.75 0.8231116310160428 0.5785817315578461 0.40567960069576897 0.6712307555060233 0.48197355627376126
28 26 27 0.78675 0.8448958333333333 0.7474798387096774 0.8270387700534759 0.5676946561336518 0.4060484048128128 0.6555941143343526 0.48230106714256304
29 27 28 0.787875 0.8460625 0.7505040322580645 0.8224431818181818 0.575938116312027 0.403180761963129 0.6507430134281036 0.48200917403328225
30 28 29 0.789 0.8495416666666666 0.7605846774193549 0.8254512032085561 0.5655779435634612 0.39154566899935406 0.6520830373610219 0.4732334581925907
31 29 30 0.790625 0.849375 0.7434475806451613 0.8205213903743316 0.5578647639751434 0.3910754985809326 0.6789213486256138 0.5025412492095468
32 30 31 0.787375 0.850125 0.7565524193548387 0.8200200534759359 0.5687701859474182 0.3879919012586276 0.649224087115257 0.48824962750475676
33 31 32 0.79575 0.8501666666666666 0.7560483870967742 0.8283756684491979 0.5432633152008056 0.3852265829642614 0.6388471222692921 0.4738096959769407
34 32 33 0.7895 0.8533125 0.7595766129032258 0.8280414438502673 0.5557173223495483 0.3842975225051244 0.6391933618053314 0.480888257131857
35 33 34 0.8546666666666667 0.8279578877005348 0.3802658775647481 0.4736704102015113
36 34 35 0.8553541666666666 0.8287934491978609 0.37693077965577443 0.47027840429448825
37 35 36 0.8574583333333333 0.8280414438502673 0.37416908142964045 0.47105003949155144
38 36 37 0.8575416666666666 0.8333890374331551 0.370725477874279 0.4729995278113666
39 37 38 0.8593333333333333 0.8318850267379679 0.3660616307258606 0.46004778090964027
40 38 39 0.86125 0.8230280748663101 0.36278441416223844 0.4792340671155542
41 39 40 0.8597291666666667 0.8328877005347594 0.36306345409154894 0.4713420571490405
42 40 41 0.8594583333333333 0.8338903743315508 0.35881871738036475 0.457705247131261
43 41 42 0.86125 0.8338903743315508 0.35548474109172823 0.4744296157583196
44 42 43 0.8638958333333333 0.8328877005347594 0.35729147561391195 0.46916984149160235
45 43 44 0.864375 0.8360628342245989 0.3560072028040886 0.45340159527439483
46 44 45 0.8649791666666666 0.829879679144385 0.35113127034902575 0.4705522551256068
47 45 46 0.8642708333333333 0.832302807486631 0.3466692521572113 0.4682676112428706
48 46 47 0.8671458333333333 0.8295454545454546 0.34586968237161636 0.4741511169601889
49 47 48 0.867125 0.8333890374331551 0.3455539164741834 0.47975461392160407
50 48 49 0.8672916666666667 0.8318014705882353 0.34170353756348293 0.4724194825811182
51 49 50 0.8685416666666667 0.830548128342246 0.33824845480918886 0.47551511706196686
52 50 51 0.8786875 0.8408255347593583 0.31427997442086536 0.45161250855195967
53 51 52 0.8811666666666667 0.8393215240641712 0.3106038907766342 0.45226032346646416
54 52 53 0.881875 0.8417446524064172 0.3050905155738195 0.44453552421082787
55 53 54 0.8818958333333333 0.8420788770053476 0.30438282175858816 0.45232303249325984
56 54 55 0.8853958333333334 0.8393215240641712 0.29754234209656716 0.45854009632120796
57 55 56 0.8851041666666667 0.8404913101604278 0.29953089368343355 0.4524733354063595
58 56 57 0.8845625 0.8411597593582888 0.29662314279874163 0.45404982789952486
59 57 58 0.8874166666666666 0.8431651069518716 0.29427229724327725 0.45166250935850294
60 58 59 0.8859375 0.8394050802139037 0.29326443988084794 0.46354111527057895
61 59 60 0.888375 0.8429979946524064 0.2878838664491971 0.4655548495086119
62 60 61 0.8886666666666667 0.8424966577540107 0.2877097588280837 0.45055208335267033
63 61 62 0.889125 0.8429144385026738 0.2842213006118933 0.4635044741917421
64 62 63 0.8885625 0.8435828877005348 0.2865720265607039 0.4594836203172245
65 63 64 0.8917708333333333 0.8379010695187166 0.285613534172376 0.4660476203111404
66 64 65 0.8910625 0.8383188502673797 0.28201638598243395 0.4701039531332924
67 65 66 0.8908958333333333 0.8407419786096256 0.2792068747878075 0.47005820457629344
68 66 67 0.8923333333333333 0.8440006684491979 0.2773614428540071 0.4646621039685081
69 67 68 0.8912291666666666 0.8459224598930482 0.28061300626397134 0.45556305787142587
70 68 69 0.8947083333333333 0.8403241978609626 0.27382597197095554 0.4730077214578894
71 69 70 0.8913958333333334 0.8402406417112299 0.2796522062718868 0.4642943452226924
72 70 71 0.8939375 0.8412433155080213 0.27323526923855146 0.4593185937022143
73 71 72 0.8947708333333333 0.841326871657754 0.2720908187329769 0.4730970057892927
74 72 73 0.8960208333333334 0.8417446524064172 0.26792943899333477 0.47570018247168333
75 73 74 0.8949791666666667 0.8415775401069518 0.27027500013510386 0.4757912041828594
76 74 75 0.9015208333333333 0.8446691176470589 0.257486442198356 0.4704125145858622
77 75 76 0.9023333333333333 0.8451704545454546 0.25169081447521846 0.46167185049962234
78 76 77 0.9014583333333334 0.8432486631016043 0.2498825814574957 0.462763199672342

BIN
data/notebook2/random_qccnn_weights.pt
View File

Binary file not shown.

BIN
data/notebook2/vgg_best.pt
View File

Binary file not shown.

185
data/notebook2/vgg_metrics.csv
View File

@ -1,86 +1,101 @@
,epoch,train_acc,valid_acc,train_loss,valid_loss ,epoch,train_acc,valid_acc,train_loss,valid_loss
0,1,0.575125,0.7011088709677419,2.031563010215759,1.8535375249001287 0,1,0.767875,0.8360628342245989,1.753534612496694,1.6362467181873832
1,2,0.723875,0.7515120967741935,1.7430778923034669,1.713461822079074 1,2,0.8333125,0.8577038770053476,1.6276749771436057,1.6030110356641962
2,3,0.76425,0.7525201612903226,1.6991203842163085,1.7051894049490652 2,3,0.8611875,0.8703208556149733,1.60025262260437,1.5910939386184202
3,4,0.779875,0.7716733870967742,1.6807003259658813,1.690080665772961 3,4,0.8715833333333334,0.8587065508021391,1.5890283988316853,1.601965536408246
4,5,0.79525,0.7696572580645161,1.6654855661392212,1.6926762519344207 4,5,0.8776041666666666,0.8759191176470589,1.5827694902420044,1.5844863908176117
5,6,0.80175,0.7888104838709677,1.6598792200088501,1.6711357831954956 5,6,0.8843958333333334,0.8757520053475936,1.5761419967015584,1.5849310975661253
6,7,0.80875,0.7721774193548387,1.6529147624969482,1.6847506146277151 6,7,0.88675,0.8812667112299465,1.573840765953064,1.5789309529697193
7,8,0.812375,0.8004032258064516,1.649049828529358,1.6597587523921844 7,8,0.8909375,0.8832720588235294,1.569781884988149,1.5779090036045422
8,9,0.815375,0.7893145161290323,1.6458229179382324,1.6707303101016628 8,9,0.8903333333333333,0.8875334224598931,1.570390274365743,1.5736284517349406
9,10,0.825,0.811491935483871,1.6370085287094116,1.6518691432091497 9,10,0.8941458333333333,0.890625,1.5664398628870646,1.5700276994450206
10,11,0.832375,0.795866935483871,1.630222158432007,1.6616583139665666 10,11,0.8940208333333334,0.8915441176470589,1.5668807325363159,1.5694875258175447
11,12,0.83225,0.8145161290322581,1.6293829317092896,1.6454557026586225 11,12,0.8958958333333333,0.8737466577540107,1.5646815473238627,1.5868047845554862
12,13,0.834875,0.8125,1.6268642024993896,1.6500283018235238 12,13,0.8980625,0.8921290106951871,1.5629661572774252,1.5691035067971377
13,14,0.840875,0.8104838709677419,1.6199358901977539,1.652194688397069 13,14,0.900625,0.8943850267379679,1.560197625319163,1.566351128771981
14,15,0.83975,0.8069556451612904,1.6210605192184449,1.6520756982987927 14,15,0.8988125,0.8884525401069518,1.561814420223236,1.572067444337243
15,16,0.84175,0.8004032258064516,1.6195698108673096,1.6582853217278757 15,16,0.8991041666666667,0.8928810160427807,1.5614849192301432,1.5675410924748303
16,17,0.838625,0.8049395161290323,1.6228710346221924,1.656198097813514 16,17,0.9010208333333334,0.8932152406417112,1.5596694407463074,1.5670097658340945
17,18,0.83775,0.8140120967741935,1.6226149969100951,1.6462942131104008 17,18,0.9034583333333334,0.8913770053475936,1.5576222189267477,1.56979562700751
18,19,0.845375,0.8251008064516129,1.6150365982055663,1.6358921681680987 18,19,0.9042083333333333,0.8852774064171123,1.5566549801826477,1.5758734877734262
19,20,0.85125,0.8296370967741935,1.6097205333709717,1.6333312757553593 19,20,0.9005833333333333,0.890625,1.560306779384613,1.5699780733190118
20,21,0.851875,0.8210685483870968,1.609424132347107,1.6388044895664338 20,21,0.91125,0.9029913101604278,1.5499087982177735,1.5577653244854932
21,22,0.850375,0.8210685483870968,1.6101643466949462,1.6369191561975787 21,22,0.9131041666666667,0.906667780748663,1.54771670850118,1.5544780492782593
22,23,0.858125,0.8185483870967742,1.6031983375549317,1.6421872877305554 22,23,0.9148125,0.9045788770053476,1.5459488903681438,1.5563749999286018
23,24,0.857125,0.8361895161290323,1.6038059520721435,1.62519553015309 23,24,0.9155833333333333,0.9033255347593583,1.5449249391555786,1.5577488563914987
24,25,0.854,0.8301411290322581,1.606280044555664,1.6290803609355804 24,25,0.9170208333333333,0.9065842245989305,1.5440529939333598,1.5541542717479766
25,26,0.858375,0.8119959677419355,1.6011180095672608,1.648349738890125 25,26,0.9180208333333333,0.9048295454545454,1.5431619186401366,1.5560473452277361
26,27,0.861375,0.8371975806451613,1.6000273780822754,1.6237776010267195 26,27,0.9175208333333333,0.9046624331550802,1.5432857065200805,1.5563587473038045
27,28,0.8705,0.8351814516129032,1.5907322645187378,1.6240986316434798 27,28,0.9199583333333333,0.9085895721925134,1.5409181524912516,1.5526812178565856
28,29,0.87175,0.828125,1.5896439476013184,1.6316479982868317 28,29,0.9184583333333334,0.9052473262032086,1.5422742649714152,1.555272618079568
29,30,0.867375,0.8266129032258065,1.5936143741607667,1.632056209348863 29,30,0.9212291666666667,0.9065006684491979,1.53969158522288,1.554516376021074
30,31,0.86575,0.8377016129032258,1.5949567575454713,1.6240303862479426 30,31,0.9207916666666667,0.9100935828877005,1.5402175769805908,1.5506398645951787
31,32,0.86975,0.8336693548387096,1.5907692136764526,1.6251203167823054 31,32,0.9214375,0.9079211229946524,1.539174134572347,1.5536619998554495
32,33,0.86975,0.8397177419354839,1.5919580411911012,1.6214879328204739 32,33,0.9203333333333333,0.9089237967914439,1.540758513132731,1.5520596727330418
33,34,0.872375,0.8422379032258065,1.5886561880111694,1.6194973222671016 33,34,0.920625,0.9049966577540107,1.5403572120666504,1.5559145416167968
34,35,0.876,0.8331653225806451,1.585767653465271,1.6247131862948019 34,35,0.9203125,0.9095086898395722,1.5404717030525208,1.551519107053624
35,36,0.871875,0.8392137096774194,1.5895709590911866,1.6215527211466143 35,36,0.9235,0.908673128342246,1.537489187558492,1.5522340115378885
36,37,0.871125,0.8245967741935484,1.590462643623352,1.6370407227546937 36,37,0.9236666666666666,0.9076704545454546,1.5371040493647257,1.5535466779362073
37,38,0.87325,0.8301411290322581,1.5876847248077393,1.6306157150576193 37,38,0.9271458333333333,0.9108455882352942,1.5338874877293904,1.550052744182036
38,39,0.8705,0.8240927419354839,1.590844289779663,1.634965923524672 38,39,0.928375,0.9119318181818182,1.5327118910153708,1.5489872643016875
39,40,0.88125,0.8402217741935484,1.5803495874404907,1.6220719968118975 39,40,0.9302916666666666,0.9157754010695187,1.530610190709432,1.5451570577162472
40,41,0.881875,0.8462701612903226,1.5788077726364136,1.614263488400367 40,41,0.9313541666666667,0.9134358288770054,1.5297347887357076,1.5474902193814037
41,42,0.87625,0.8487903225806451,1.5843929862976074,1.6131737078389814 41,42,0.9315208333333334,0.9144385026737968,1.5294018096923827,1.546497144163611
42,43,0.88175,0.842741935483871,1.5789586782455445,1.6184405088424683 42,43,0.9323125,0.9160260695187166,1.5288680585225423,1.5444984174667196
43,44,0.880375,0.8417338709677419,1.5802030544281005,1.6189708786626016 43,44,0.9319791666666667,0.9151069518716578,1.5289348866144816,1.5459555961231497
44,45,0.880375,0.8492943548387096,1.5803771505355835,1.610948174230514 44,45,0.9333541666666667,0.9186163101604278,1.5275377634366354,1.5426336552370041
45,46,0.877625,0.8523185483870968,1.5828620948791503,1.6089561793111986 45,46,0.932375,0.9125167112299465,1.528664146900177,1.5481219285312184
46,47,0.882125,0.8442540322580645,1.578727219581604,1.6160847948443504 46,47,0.932375,0.9180314171122995,1.528616013844808,1.543393959973585
47,48,0.872875,0.8392137096774194,1.5874832077026366,1.6228746021947553 47,48,0.9353541666666667,0.9174465240641712,1.5259391600290935,1.5431863923761295
48,49,0.884125,0.8371975806451613,1.5771635084152222,1.6237398655183855 48,49,0.9332291666666667,0.9116811497326203,1.527786935488383,1.5487734449101005
49,50,0.88975,0.8341733870967742,1.5712118272781372,1.6256768280459988 49,50,0.9352916666666666,0.9159425133689839,1.525529363632202,1.5448988389203893
50,51,0.876,0.8432459677419355,1.585065812110901,1.6188401445265739 50,51,0.9351666666666667,0.9190340909090909,1.5257512016296386,1.541433523682987
51,52,0.883,0.844758064516129,1.5785351629257203,1.6169025359615203 51,52,0.9358125,0.9166945187165776,1.525342579046885,1.5442416878307568
52,53,0.889125,0.8548387096774194,1.5723771095275878,1.607426397262081 52,53,0.9355625,0.9197860962566845,1.5253059350649516,1.5413460323517336
53,54,0.88625,0.8518145161290323,1.5749757404327394,1.6076742141477522 53,54,0.936625,0.9142713903743316,1.5245349135398865,1.5465437422461688
54,55,0.891125,0.8452620967741935,1.5695797872543336,1.6156867473356185 54,55,0.9349791666666667,0.9161931818181818,1.525785480340322,1.5452430726372621
55,56,0.891625,0.8497983870967742,1.5691107511520386,1.6118658050414054 55,56,0.9368333333333333,0.9174465240641712,1.524029705842336,1.5432787445139757
56,57,0.883375,0.8508064516129032,1.577266471862793,1.6087883749315817 56,57,0.9355833333333333,0.9158589572192514,1.5253107420603433,1.5446410478755115
57,58,0.891625,0.8422379032258065,1.5702907581329346,1.6168161553721274 57,58,0.9371875,0.9207052139037433,1.524094797929128,1.5405435536634475
58,59,0.89375,0.8553427419354839,1.5679762859344482,1.6071604336461713 58,59,0.9376458333333333,0.9199532085561497,1.5234766112963358,1.5406819996349315
59,60,0.885875,0.8482862903225806,1.5749410953521727,1.6108381056016492 59,60,0.9391875,0.9189505347593583,1.5217385093371074,1.5418526864944295
60,61,0.891875,0.8417338709677419,1.5696327953338622,1.6187968907817718 60,61,0.9380208333333333,0.9172794117647058,1.5229359103838602,1.54353828162433
61,62,0.894,0.8392137096774194,1.5671770153045654,1.6208721822307957 61,62,0.9387708333333333,0.9206216577540107,1.5224510963757834,1.5403235111644562
62,63,0.891125,0.8392137096774194,1.569726734161377,1.6224797733368412 62,63,0.93975,0.9156082887700535,1.5212798911730447,1.545105798996706
63,64,0.89325,0.8518145161290323,1.568245210647583,1.606977516605008 63,64,0.9397708333333333,0.921875,1.5213380891482036,1.53904527202647
64,65,0.895125,0.8462701612903226,1.5658181638717652,1.6140611633177726 64,65,0.9388541666666667,0.9197860962566845,1.5220589057604472,1.5410850934166322
65,66,0.89175,0.8568548387096774,1.5686321334838866,1.6044510756769488 65,66,0.9384166666666667,0.9163602941176471,1.5225912384986877,1.5446943541899085
66,67,0.896375,0.8412298387096774,1.5650024271011354,1.6208048520549652 66,67,0.9405,0.9212901069518716,1.5205388652483622,1.539675323083439
67,68,0.8895,0.8477822580645161,1.571241024017334,1.6136699338113107 67,68,0.9412291666666667,0.9225434491978609,1.519922403494517,1.53815110800738
68,69,0.901625,0.8472782258064516,1.5600450325012207,1.612250724146443 68,69,0.9401041666666666,0.9145220588235294,1.520717616558075,1.5464129702930145
69,70,0.89025,0.8306451612903226,1.5705311574935914,1.630635638390818 69,70,0.9411875,0.921875,1.5197122866312662,1.5391668482897753
70,71,0.89675,0.8538306451612904,1.5637341051101685,1.6056317244806597 70,71,0.94,0.9188669786096256,1.5209512915611267,1.5418487353758379
71,72,0.897,0.8412298387096774,1.5633089447021484,1.6192954970944313 71,72,0.9394583333333333,0.9202874331550802,1.5213834778467814,1.540625613003491
72,73,0.900375,0.8503024193548387,1.560647201538086,1.6097132775091356 72,73,0.9419583333333333,0.9192012032085561,1.5191686747868856,1.5421639017880282
73,74,0.895625,0.8533266129032258,1.565330421447754,1.6075265484471475 73,74,0.9420208333333333,0.9211229946524064,1.5191353003184,1.539851359505067
74,75,0.895125,0.8543346774193549,1.565690894126892,1.6060891266792052 74,75,0.9431458333333333,0.9225434491978609,1.517710240205129,1.5381846899654776
75,76,0.900625,0.8608870967741935,1.560530616760254,1.6011101891917567 75,76,0.9452708333333333,0.9207887700534759,1.5158586444854736,1.5403157555483242
76,77,0.897125,0.8563508064516129,1.563725378036499,1.6037284789546844 76,77,0.9455625,0.9209558823529411,1.5154005877176921,1.539823994917028
77,78,0.89175,0.8482862903225806,1.5693257989883422,1.6122698245509979 77,78,0.9458333333333333,0.9228776737967914,1.515006558418274,1.5379077584985743
78,79,0.90225,0.8487903225806451,1.5589981718063355,1.6111104180735927 78,79,0.9461041666666666,0.9209558823529411,1.5149241960843405,1.5400247025617304
79,80,0.893375,0.8442540322580645,1.5669814805984497,1.6161983090062295 79,80,0.9460208333333333,0.9239639037433155,1.515042960802714,1.5368424086647237
80,81,0.897125,0.8573588709677419,1.56400607585907,1.6040064134905416 80,81,0.9453541666666667,0.9212065508021391,1.515584836324056,1.5400443440452616
81,82,0.898,0.8568548387096774,1.5621892538070679,1.6044225615839804 81,82,0.9463958333333333,0.9239639037433155,1.5146392253239949,1.5368295028247936
82,83,0.89075,0.8503024193548387,1.5697740039825439,1.6114465228972896 82,83,0.9471041666666666,0.9226270053475936,1.514121623357137,1.5383771377451279
83,84,0.900625,0.8598790322580645,1.5606124105453492,1.6002429416102748 83,84,0.946625,0.9215407754010695,1.5143028028806051,1.5394194024131898
84,85,0.89825,0.8553427419354839,1.5628600664138794,1.603792409743032 84,85,0.9472916666666666,0.9249665775401069,1.5138665714263917,1.5362410226607706
85,86,0.9468958333333334,0.9239639037433155,1.5140059588750203,1.5370322306525899
86,87,0.947625,0.9238803475935828,1.513320836544037,1.537034041741315
87,88,0.948375,0.9229612299465241,1.5128038795789083,1.5373781154499973
88,89,0.9495,0.9250501336898396,1.5117765822410583,1.5355126124652312
89,90,0.9491458333333334,0.9232118983957219,1.512057636419932,1.537534661471525
90,91,0.9485,0.9240474598930482,1.5127018653551738,1.537239743426522
91,92,0.9492083333333333,0.921457219251337,1.5120360770225525,1.53860371316818
92,93,0.95,0.9224598930481284,1.5111351316769919,1.5382829611314173
93,94,0.9503125,0.9248830213903744,1.510804171562195,1.5363529123724464
94,95,0.9513333333333334,0.9275568181818182,1.509633824825287,1.533667146840835
95,96,0.9501041666666666,0.9229612299465241,1.5108498128255208,1.5375941335198713
96,97,0.9505833333333333,0.9207887700534759,1.5104362696011862,1.5394581116457036
97,98,0.95125,0.926052807486631,1.5097919216156006,1.5350576141938805
98,99,0.950875,0.9257185828877005,1.5103401794433593,1.5352602616988402
99,100,0.9509166666666666,0.9251336898395722,1.5100935606956483,1.5362022280055572

1 epoch train_acc valid_acc train_loss valid_loss
2 0 1 0.575125 0.767875 0.7011088709677419 0.8360628342245989 2.031563010215759 1.753534612496694 1.8535375249001287 1.6362467181873832
3 1 2 0.723875 0.8333125 0.7515120967741935 0.8577038770053476 1.7430778923034669 1.6276749771436057 1.713461822079074 1.6030110356641962
4 2 3 0.76425 0.8611875 0.7525201612903226 0.8703208556149733 1.6991203842163085 1.60025262260437 1.7051894049490652 1.5910939386184202
5 3 4 0.779875 0.8715833333333334 0.7716733870967742 0.8587065508021391 1.6807003259658813 1.5890283988316853 1.690080665772961 1.601965536408246
6 4 5 0.79525 0.8776041666666666 0.7696572580645161 0.8759191176470589 1.6654855661392212 1.5827694902420044 1.6926762519344207 1.5844863908176117
7 5 6 0.80175 0.8843958333333334 0.7888104838709677 0.8757520053475936 1.6598792200088501 1.5761419967015584 1.6711357831954956 1.5849310975661253
8 6 7 0.80875 0.88675 0.7721774193548387 0.8812667112299465 1.6529147624969482 1.573840765953064 1.6847506146277151 1.5789309529697193
9 7 8 0.812375 0.8909375 0.8004032258064516 0.8832720588235294 1.649049828529358 1.569781884988149 1.6597587523921844 1.5779090036045422
10 8 9 0.815375 0.8903333333333333 0.7893145161290323 0.8875334224598931 1.6458229179382324 1.570390274365743 1.6707303101016628 1.5736284517349406
11 9 10 0.825 0.8941458333333333 0.811491935483871 0.890625 1.6370085287094116 1.5664398628870646 1.6518691432091497 1.5700276994450206
12 10 11 0.832375 0.8940208333333334 0.795866935483871 0.8915441176470589 1.630222158432007 1.5668807325363159 1.6616583139665666 1.5694875258175447
13 11 12 0.83225 0.8958958333333333 0.8145161290322581 0.8737466577540107 1.6293829317092896 1.5646815473238627 1.6454557026586225 1.5868047845554862
14 12 13 0.834875 0.8980625 0.8125 0.8921290106951871 1.6268642024993896 1.5629661572774252 1.6500283018235238 1.5691035067971377
15 13 14 0.840875 0.900625 0.8104838709677419 0.8943850267379679 1.6199358901977539 1.560197625319163 1.652194688397069 1.566351128771981
16 14 15 0.83975 0.8988125 0.8069556451612904 0.8884525401069518 1.6210605192184449 1.561814420223236 1.6520756982987927 1.572067444337243
17 15 16 0.84175 0.8991041666666667 0.8004032258064516 0.8928810160427807 1.6195698108673096 1.5614849192301432 1.6582853217278757 1.5675410924748303
18 16 17 0.838625 0.9010208333333334 0.8049395161290323 0.8932152406417112 1.6228710346221924 1.5596694407463074 1.656198097813514 1.5670097658340945
19 17 18 0.83775 0.9034583333333334 0.8140120967741935 0.8913770053475936 1.6226149969100951 1.5576222189267477 1.6462942131104008 1.56979562700751
20 18 19 0.845375 0.9042083333333333 0.8251008064516129 0.8852774064171123 1.6150365982055663 1.5566549801826477 1.6358921681680987 1.5758734877734262
21 19 20 0.85125 0.9005833333333333 0.8296370967741935 0.890625 1.6097205333709717 1.560306779384613 1.6333312757553593 1.5699780733190118
22 20 21 0.851875 0.91125 0.8210685483870968 0.9029913101604278 1.609424132347107 1.5499087982177735 1.6388044895664338 1.5577653244854932
23 21 22 0.850375 0.9131041666666667 0.8210685483870968 0.906667780748663 1.6101643466949462 1.54771670850118 1.6369191561975787 1.5544780492782593
24 22 23 0.858125 0.9148125 0.8185483870967742 0.9045788770053476 1.6031983375549317 1.5459488903681438 1.6421872877305554 1.5563749999286018
25 23 24 0.857125 0.9155833333333333 0.8361895161290323 0.9033255347593583 1.6038059520721435 1.5449249391555786 1.62519553015309 1.5577488563914987
26 24 25 0.854 0.9170208333333333 0.8301411290322581 0.9065842245989305 1.606280044555664 1.5440529939333598 1.6290803609355804 1.5541542717479766
27 25 26 0.858375 0.9180208333333333 0.8119959677419355 0.9048295454545454 1.6011180095672608 1.5431619186401366 1.648349738890125 1.5560473452277361
28 26 27 0.861375 0.9175208333333333 0.8371975806451613 0.9046624331550802 1.6000273780822754 1.5432857065200805 1.6237776010267195 1.5563587473038045
29 27 28 0.8705 0.9199583333333333 0.8351814516129032 0.9085895721925134 1.5907322645187378 1.5409181524912516 1.6240986316434798 1.5526812178565856
30 28 29 0.87175 0.9184583333333334 0.828125 0.9052473262032086 1.5896439476013184 1.5422742649714152 1.6316479982868317 1.555272618079568
31 29 30 0.867375 0.9212291666666667 0.8266129032258065 0.9065006684491979 1.5936143741607667 1.53969158522288 1.632056209348863 1.554516376021074
32 30 31 0.86575 0.9207916666666667 0.8377016129032258 0.9100935828877005 1.5949567575454713 1.5402175769805908 1.6240303862479426 1.5506398645951787
33 31 32 0.86975 0.9214375 0.8336693548387096 0.9079211229946524 1.5907692136764526 1.539174134572347 1.6251203167823054 1.5536619998554495
34 32 33 0.86975 0.9203333333333333 0.8397177419354839 0.9089237967914439 1.5919580411911012 1.540758513132731 1.6214879328204739 1.5520596727330418
35 33 34 0.872375 0.920625 0.8422379032258065 0.9049966577540107 1.5886561880111694 1.5403572120666504 1.6194973222671016 1.5559145416167968
36 34 35 0.876 0.9203125 0.8331653225806451 0.9095086898395722 1.585767653465271 1.5404717030525208 1.6247131862948019 1.551519107053624
37 35 36 0.871875 0.9235 0.8392137096774194 0.908673128342246 1.5895709590911866 1.537489187558492 1.6215527211466143 1.5522340115378885
38 36 37 0.871125 0.9236666666666666 0.8245967741935484 0.9076704545454546 1.590462643623352 1.5371040493647257 1.6370407227546937 1.5535466779362073
39 37 38 0.87325 0.9271458333333333 0.8301411290322581 0.9108455882352942 1.5876847248077393 1.5338874877293904 1.6306157150576193 1.550052744182036
40 38 39 0.8705 0.928375 0.8240927419354839 0.9119318181818182 1.590844289779663 1.5327118910153708 1.634965923524672 1.5489872643016875
41 39 40 0.88125 0.9302916666666666 0.8402217741935484 0.9157754010695187 1.5803495874404907 1.530610190709432 1.6220719968118975 1.5451570577162472
42 40 41 0.881875 0.9313541666666667 0.8462701612903226 0.9134358288770054 1.5788077726364136 1.5297347887357076 1.614263488400367 1.5474902193814037
43 41 42 0.87625 0.9315208333333334 0.8487903225806451 0.9144385026737968 1.5843929862976074 1.5294018096923827 1.6131737078389814 1.546497144163611
44 42 43 0.88175 0.9323125 0.842741935483871 0.9160260695187166 1.5789586782455445 1.5288680585225423 1.6184405088424683 1.5444984174667196
45 43 44 0.880375 0.9319791666666667 0.8417338709677419 0.9151069518716578 1.5802030544281005 1.5289348866144816 1.6189708786626016 1.5459555961231497
46 44 45 0.880375 0.9333541666666667 0.8492943548387096 0.9186163101604278 1.5803771505355835 1.5275377634366354 1.610948174230514 1.5426336552370041
47 45 46 0.877625 0.932375 0.8523185483870968 0.9125167112299465 1.5828620948791503 1.528664146900177 1.6089561793111986 1.5481219285312184
48 46 47 0.882125 0.932375 0.8442540322580645 0.9180314171122995 1.578727219581604 1.528616013844808 1.6160847948443504 1.543393959973585
49 47 48 0.872875 0.9353541666666667 0.8392137096774194 0.9174465240641712 1.5874832077026366 1.5259391600290935 1.6228746021947553 1.5431863923761295
50 48 49 0.884125 0.9332291666666667 0.8371975806451613 0.9116811497326203 1.5771635084152222 1.527786935488383 1.6237398655183855 1.5487734449101005
51 49 50 0.88975 0.9352916666666666 0.8341733870967742 0.9159425133689839 1.5712118272781372 1.525529363632202 1.6256768280459988 1.5448988389203893
52 50 51 0.876 0.9351666666666667 0.8432459677419355 0.9190340909090909 1.585065812110901 1.5257512016296386 1.6188401445265739 1.541433523682987
53 51 52 0.883 0.9358125 0.844758064516129 0.9166945187165776 1.5785351629257203 1.525342579046885 1.6169025359615203 1.5442416878307568
54 52 53 0.889125 0.9355625 0.8548387096774194 0.9197860962566845 1.5723771095275878 1.5253059350649516 1.607426397262081 1.5413460323517336
55 53 54 0.88625 0.936625 0.8518145161290323 0.9142713903743316 1.5749757404327394 1.5245349135398865 1.6076742141477522 1.5465437422461688
56 54 55 0.891125 0.9349791666666667 0.8452620967741935 0.9161931818181818 1.5695797872543336 1.525785480340322 1.6156867473356185 1.5452430726372621
57 55 56 0.891625 0.9368333333333333 0.8497983870967742 0.9174465240641712 1.5691107511520386 1.524029705842336 1.6118658050414054 1.5432787445139757
58 56 57 0.883375 0.9355833333333333 0.8508064516129032 0.9158589572192514 1.577266471862793 1.5253107420603433 1.6087883749315817 1.5446410478755115
59 57 58 0.891625 0.9371875 0.8422379032258065 0.9207052139037433 1.5702907581329346 1.524094797929128 1.6168161553721274 1.5405435536634475
60 58 59 0.89375 0.9376458333333333 0.8553427419354839 0.9199532085561497 1.5679762859344482 1.5234766112963358 1.6071604336461713 1.5406819996349315
61 59 60 0.885875 0.9391875 0.8482862903225806 0.9189505347593583 1.5749410953521727 1.5217385093371074 1.6108381056016492 1.5418526864944295
62 60 61 0.891875 0.9380208333333333 0.8417338709677419 0.9172794117647058 1.5696327953338622 1.5229359103838602 1.6187968907817718 1.54353828162433
63 61 62 0.894 0.9387708333333333 0.8392137096774194 0.9206216577540107 1.5671770153045654 1.5224510963757834 1.6208721822307957 1.5403235111644562
64 62 63 0.891125 0.93975 0.8392137096774194 0.9156082887700535 1.569726734161377 1.5212798911730447 1.6224797733368412 1.545105798996706
65 63 64 0.89325 0.9397708333333333 0.8518145161290323 0.921875 1.568245210647583 1.5213380891482036 1.606977516605008 1.53904527202647
66 64 65 0.895125 0.9388541666666667 0.8462701612903226 0.9197860962566845 1.5658181638717652 1.5220589057604472 1.6140611633177726 1.5410850934166322
67 65 66 0.89175 0.9384166666666667 0.8568548387096774 0.9163602941176471 1.5686321334838866 1.5225912384986877 1.6044510756769488 1.5446943541899085
68 66 67 0.896375 0.9405 0.8412298387096774 0.9212901069518716 1.5650024271011354 1.5205388652483622 1.6208048520549652 1.539675323083439
69 67 68 0.8895 0.9412291666666667 0.8477822580645161 0.9225434491978609 1.571241024017334 1.519922403494517 1.6136699338113107 1.53815110800738
70 68 69 0.901625 0.9401041666666666 0.8472782258064516 0.9145220588235294 1.5600450325012207 1.520717616558075 1.612250724146443 1.5464129702930145
71 69 70 0.89025 0.9411875 0.8306451612903226 0.921875 1.5705311574935914 1.5197122866312662 1.630635638390818 1.5391668482897753
72 70 71 0.89675 0.94 0.8538306451612904 0.9188669786096256 1.5637341051101685 1.5209512915611267 1.6056317244806597 1.5418487353758379
73 71 72 0.897 0.9394583333333333 0.8412298387096774 0.9202874331550802 1.5633089447021484 1.5213834778467814 1.6192954970944313 1.540625613003491
74 72 73 0.900375 0.9419583333333333 0.8503024193548387 0.9192012032085561 1.560647201538086 1.5191686747868856 1.6097132775091356 1.5421639017880282
75 73 74 0.895625 0.9420208333333333 0.8533266129032258 0.9211229946524064 1.565330421447754 1.5191353003184 1.6075265484471475 1.539851359505067
76 74 75 0.895125 0.9431458333333333 0.8543346774193549 0.9225434491978609 1.565690894126892 1.517710240205129 1.6060891266792052 1.5381846899654776
77 75 76 0.900625 0.9452708333333333 0.8608870967741935 0.9207887700534759 1.560530616760254 1.5158586444854736 1.6011101891917567 1.5403157555483242
78 76 77 0.897125 0.9455625 0.8563508064516129 0.9209558823529411 1.563725378036499 1.5154005877176921 1.6037284789546844 1.539823994917028
79 77 78 0.89175 0.9458333333333333 0.8482862903225806 0.9228776737967914 1.5693257989883422 1.515006558418274 1.6122698245509979 1.5379077584985743
80 78 79 0.90225 0.9461041666666666 0.8487903225806451 0.9209558823529411 1.5589981718063355 1.5149241960843405 1.6111104180735927 1.5400247025617304
81 79 80 0.893375 0.9460208333333333 0.8442540322580645 0.9239639037433155 1.5669814805984497 1.515042960802714 1.6161983090062295 1.5368424086647237
82 80 81 0.897125 0.9453541666666667 0.8573588709677419 0.9212065508021391 1.56400607585907 1.515584836324056 1.6040064134905416 1.5400443440452616
83 81 82 0.898 0.9463958333333333 0.8568548387096774 0.9239639037433155 1.5621892538070679 1.5146392253239949 1.6044225615839804 1.5368295028247936
84 82 83 0.89075 0.9471041666666666 0.8503024193548387 0.9226270053475936 1.5697740039825439 1.514121623357137 1.6114465228972896 1.5383771377451279
85 83 84 0.900625 0.946625 0.8598790322580645 0.9215407754010695 1.5606124105453492 1.5143028028806051 1.6002429416102748 1.5394194024131898
86 84 85 0.89825 0.9472916666666666 0.8553427419354839 0.9249665775401069 1.5628600664138794 1.5138665714263917 1.603792409743032 1.5362410226607706
87 85 86 0.9468958333333334 0.9239639037433155 1.5140059588750203 1.5370322306525899
88 86 87 0.947625 0.9238803475935828 1.513320836544037 1.537034041741315
89 87 88 0.948375 0.9229612299465241 1.5128038795789083 1.5373781154499973
90 88 89 0.9495 0.9250501336898396 1.5117765822410583 1.5355126124652312
91 89 90 0.9491458333333334 0.9232118983957219 1.512057636419932 1.537534661471525
92 90 91 0.9485 0.9240474598930482 1.5127018653551738 1.537239743426522
93 91 92 0.9492083333333333 0.921457219251337 1.5120360770225525 1.53860371316818
94 92 93 0.95 0.9224598930481284 1.5111351316769919 1.5382829611314173
95 93 94 0.9503125 0.9248830213903744 1.510804171562195 1.5363529123724464
96 94 95 0.9513333333333334 0.9275568181818182 1.509633824825287 1.533667146840835
97 95 96 0.9501041666666666 0.9229612299465241 1.5108498128255208 1.5375941335198713
98 96 97 0.9505833333333333 0.9207887700534759 1.5104362696011862 1.5394581116457036
99 97 98 0.95125 0.926052807486631 1.5097919216156006 1.5350576141938805
100 98 99 0.950875 0.9257185828877005 1.5103401794433593 1.5352602616988402
101 99 100 0.9509166666666666 0.9251336898395722 1.5100935606956483 1.5362022280055572

BIN
data/notebook2/vgg_weights.pt
View File

Binary file not shown.