Hi can anyone check my code im not sure what wrong but when i train my module my loss always high with out going down
def train14(dataloader,net):
net = load_net(net, 'gpu')
net = net.cuda()
epoch = 30
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
train_loss = list()
#set_trace()
for i in range(epoch):
for i, data in enumerate(dataloader):
inps, labs = data
inps, labs = inps.cuda(args['device']), labs.cuda(args['device'])
inps = Variable(inps).cuda(args['device'])
labs = Variable(labs).cuda(args['device'])
optimizer.zero_grad()
outs = net(inps.permute(0, 3, 1, 2).float())
soft_outs = F.softmax(outs, dim=1)
prds = soft_outs.data.max(1)[1]
loss = criterion(outs, labs)
loss.backward()
optimizer.step()
prds = prds.cpu().numpy()
inps_np = inps.detach().cpu().numpy()
labs_np = labs.detach().cpu().numpy()
train_loss.append(loss.data.item
())
print('[epoch %d], [iter %d / %d], [train loss %.5f]' % (epoch, i + 1, len(dataloader), np.asarray(train_loss).mean()))
return net
x=train14(dataloadertrain,net='mobiface')
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/first_stage.py:32: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.
img = Variable(torch.FloatTensor(_preprocess(img)), volatile=True)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/first_stage.py:32: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.
img = Variable(torch.FloatTensor(_preprocess(img)), volatile=True)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/get_nets.py:74: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
a = F.softmax(a)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/get_nets.py:74: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
a = F.softmax(a)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/detector.py:79: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.
img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/detector.py:79: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.
img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/get_nets.py:120: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
a = F.softmax(a)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/detector.py:100: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.
img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/get_nets.py:120: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
a = F.softmax(a)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/detector.py:100: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.
img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/get_nets.py:174: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
a = F.softmax(a)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/matlab_cp2tform.py:312: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
r, _, _, _ = lstsq(X, U)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/mtcnn_network/get_nets.py:174: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
a = F.softmax(a)
/content/drive/My Drive/recfaces13/recfaces/preprocessing/matlab_cp2tform.py:312: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
r, _, _, _ = lstsq(X, U)
[epoch 30], [iter 1 / 182], [train loss 13.67538]
[epoch 30], [iter 2 / 182], [train loss 13.93409]
[epoch 30], [iter 3 / 182], [train loss 9.88422]
[epoch 30], [iter 4 / 182], [train loss 7.42359]
[epoch 30], [iter 5 / 182], [train loss 9.99569]
[epoch 30], [iter 6 / 182], [train loss 10.49389]
[epoch 30], [iter 7 / 182], [train loss 8.99476]
[epoch 30], [iter 8 / 182], [train loss 7.91546]
[epoch 30], [iter 9 / 182], [train loss 7.10814]
[epoch 30], [iter 10 / 182], [train loss 7.86791]
[epoch 30], [iter 11 / 182], [train loss 7.16874]
[epoch 30], [iter 12 / 182], [train loss 7.92612]
[epoch 30], [iter 13 / 182], [train loss 8.45253]
[epoch 30], [iter 14 / 182], [train loss 7.84907]
[epoch 30], [iter 15 / 182], [train loss 7.39011]
[epoch 30], [iter 16 / 182], [train loss 6.95442]
[epoch 30], [iter 17 / 182], [train loss 6.97154]
[epoch 30], [iter 18 / 182], [train loss 7.10896]
[epoch 30], [iter 19 / 182], [train loss 6.73483]
[epoch 30], [iter 20 / 182], [train loss 6.55003]
[epoch 30], [iter 21 / 182], [train loss 6.23812]
[epoch 30], [iter 22 / 182], [train loss 5.95457]
[epoch 30], [iter 23 / 182], [train loss 7.43152]
[epoch 30], [iter 24 / 182], [train loss 8.65758]
[epoch 30], [iter 25 / 182], [train loss 9.61982]
[epoch 30], [iter 26 / 182], [train loss 9.24982]
[epoch 30], [iter 27 / 182], [train loss 9.32092]
[epoch 30], [iter 28 / 182], [train loss 9.76417]
[epoch 30], [iter 29 / 182], [train loss 10.52662]
[epoch 30], [iter 30 / 182], [train loss 10.17573]
[epoch 30], [iter 31 / 182], [train loss 9.84750]
[epoch 30], [iter 32 / 182], [train loss 9.54338]
[epoch 30], [iter 33 / 182], [train loss 9.25418]
[epoch 30], [iter 34 / 182], [train loss 9.64890]
[epoch 30], [iter 35 / 182], [train loss 9.79242]
[epoch 30], [iter 36 / 182], [train loss 9.52817]
[epoch 30], [iter 37 / 182], [train loss 9.99964]
[epoch 30], [iter 38 / 182], [train loss 9.74174]
[epoch 30], [iter 39 / 182], [train loss 9.49257]
[epoch 30], [iter 40 / 182], [train loss 9.25540]
[epoch 30], [iter 41 / 182], [train loss 9.02966]
[epoch 30], [iter 42 / 182], [train loss 9.11816]
[epoch 30], [iter 43 / 182], [train loss 9.05369]
[epoch 30], [iter 44 / 182], [train loss 8.84793]
[epoch 30], [iter 45 / 182], [train loss 8.90156]
[epoch 30], [iter 46 / 182], [train loss 8.70805]
[epoch 30], [iter 47 / 182], [train loss 8.52278]
[epoch 30], [iter 48 / 182], [train loss 8.90073]
[epoch 30], [iter 49 / 182], [train loss 8.71908]
[epoch 30], [iter 50 / 182], [train loss 8.82156]
[epoch 30], [iter 51 / 182], [train loss 9.41688]
[epoch 30], [iter 52 / 182], [train loss 9.23589]
[epoch 30], [iter 53 / 182], [train loss 9.27772]
[epoch 30], [iter 54 / 182], [train loss 9.30042]
[epoch 30], [iter 55 / 182], [train loss 9.18761]
[epoch 30], [iter 56 / 182], [train loss 9.02356]
[epoch 30], [iter 57 / 182], [train loss 8.86526]
[epoch 30], [iter 58 / 182], [train loss 8.87040]
[epoch 30], [iter 59 / 182], [train loss 8.86168]
[epoch 30], [iter 60 / 182], [train loss 9.05313]
[epoch 30], [iter 61 / 182], [train loss 9.44328]
[epoch 30], [iter 62 / 182], [train loss 9.29097]
[epoch 30], [iter 63 / 182], [train loss 9.14349]
[epoch 30], [iter 64 / 182], [train loss 9.19337]
[epoch 30], [iter 65 / 182], [train loss 9.81524]
[epoch 30], [iter 66 / 182], [train loss 9.78365]
[epoch 30], [iter 67 / 182], [train loss 10.09947]
[epoch 30], [iter 68 / 182], [train loss 10.36468]
[epoch 30], [iter 69 / 182], [train loss 10.43877]
[epoch 30], [iter 70 / 182], [train loss 10.39080]
[epoch 30], [iter 71 / 182], [train loss 10.24445]
[epoch 30], [iter 72 / 182], [train loss 10.10217]
[epoch 30], [iter 73 / 182], [train loss 9.96378]
[epoch 30], [iter 74 / 182], [train loss 10.02074]
[epoch 30], [iter 75 / 182], [train loss 10.24865]
[epoch 30], [iter 76 / 182], [train loss 10.32667]
[epoch 30], [iter 77 / 182], [train loss 10.39449]
[epoch 30], [iter 78 / 182], [train loss 10.33688]
[epoch 30], [iter 79 / 182], [train loss 10.86841]
[epoch 30], [iter 80 / 182], [train loss 10.74629]
[epoch 30], [iter 81 / 182], [train loss 10.61362]
[epoch 30], [iter 82 / 182], [train loss 10.50374]
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7fce549480b8>>
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1101, in __del__
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7fce549480b8>>
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1101, in __del__
self._shutdown_workers()
self._shutdown_workers()
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1075, in _shutdown_workers
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1075, in _shutdown_workers
w.join(timeout=_utils.MP_STATUS_CHECK_INTERVAL)
File "/usr/lib/python3.6/multiprocessing/process.py", line 122, in join
w.join(timeout=_utils.MP_STATUS_CHECK_INTERVAL)
File "/usr/lib/python3.6/multiprocessing/process.py", line 122, in join
assert self._parent_pid == os.getpid(), 'can only join a child process'
AssertionError: can only join a child process
assert self._parent_pid == os.getpid(), 'can only join a child process'
AssertionError: can only join a child process
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7fce54338400>>
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7fce54338400>>
Traceback (most recent call last):
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1101, in __del__
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1101, in __del__
self._shutdown_workers()
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1075, in _shutdown_workers
w.join(timeout=_utils.MP_STATUS_CHECK_INTERVAL)
self._shutdown_workers()
File "/usr/lib/python3.6/multiprocessing/process.py", line 122, in join
assert self._parent_pid == os.getpid(), 'can only join a child process'
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1075, in _shutdown_workers
w.join(timeout=_utils.MP_STATUS_CHECK_INTERVAL)
File "/usr/lib/python3.6/multiprocessing/process.py", line 122, in join
AssertionError: can only join a child process
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7fce54115ba8>>
Traceback (most recent call last):
assert self._parent_pid == os.getpid(), 'can only join a child process'
AssertionError: can only join a child process
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1101, in __del__
self._shutdown_workers()
Exception ignored in: <bound method _MultiProcessingDataLoaderIter.__del__ of <torch.utils.data.dataloader._MultiProcessingDataLoaderIter object at 0x7fce54115ba8>>
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1101, in __del__
self._shutdown_workers()
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1075, in _shutdown_workers
w.join(timeout=_utils.MP_STATUS_CHECK_INTERVAL)
File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 1075, in _shutdown_workers
File "/usr/lib/python3.6/multiprocessing/process.py", line 122, in join
w.join(timeout=_utils.MP_STATUS_CHECK_INTERVAL)
File "/usr/lib/python3.6/multiprocessing/process.py", line 122, in join
assert self._parent_pid == os.getpid(), 'can only join a child process'
assert self._parent_pid == os.getpid(), 'can only join a child process'
AssertionError: can only join a child process
AssertionError: can only join a child process
[epoch 30], [iter 83 / 182], [train loss 10.62443]
[epoch 30], [iter 84 / 182], [train loss 10.49795]
[epoch 30], [iter 85 / 182], [train loss 10.37444]
[epoch 30], [iter 86 / 182], [train loss 10.78173]
[epoch 30], [iter 87 / 182], [train loss 10.94274]
[epoch 30], [iter 88 / 182], [train loss 11.21831]
[epoch 30], [iter 89 / 182], [train loss 11.64633]
[epoch 30], [iter 90 / 182], [train loss 11.78724]
[epoch 30], [iter 91 / 182], [train loss 11.65771]
[epoch 30], [iter 92 / 182], [train loss 11.91948]
[epoch 30], [iter 93 / 182], [train loss 11.92936]
[epoch 30], [iter 94 / 182], [train loss 11.80245]
[epoch 30], [iter 95 / 182], [train loss 11.67822]
[epoch 30], [iter 96 / 182], [train loss 11.55657]
[epoch 30], [iter 97 / 182], [train loss 12.20565]
[epoch 30], [iter 98 / 182], [train loss 12.65326]
[epoch 30], [iter 99 / 182], [train loss 12.79071]
[epoch 30], [iter 100 / 182], [train loss 12.75293]
[epoch 30], [iter 101 / 182], [train loss 12.98185]
[epoch 30], [iter 102 / 182], [train loss 13.01299]
[epoch 30], [iter 103 / 182], [train loss 13.11844]
[epoch 30], [iter 104 / 182], [train loss 13.23922]
[epoch 30], [iter 105 / 182], [train loss 13.16908]
[epoch 30], [iter 106 / 182], [train loss 13.09564]
[epoch 30], [iter 107 / 182], [train loss 12.97327]
[epoch 30], [iter 108 / 182], [train loss 12.85315]
[epoch 30], [iter 109 / 182], [train loss 12.73523]
[epoch 30], [iter 110 / 182], [train loss 12.62138]
[epoch 30], [iter 111 / 182], [train loss 12.58768]
[epoch 30], [iter 112 / 182], [train loss 12.92546]
[epoch 30], [iter 113 / 182], [train loss 13.38524]
[epoch 30], [iter 114 / 182], [train loss 13.70754]
[epoch 30], [iter 115 / 182], [train loss 13.99418]
[epoch 30], [iter 116 / 182], [train loss 14.29291]
[epoch 30], [iter 117 / 182], [train loss 14.17113]
[epoch 30], [iter 118 / 182], [train loss 14.09050]
[epoch 30], [iter 119 / 182], [train loss 14.19034]
[epoch 30], [iter 120 / 182], [train loss 14.28804]
[epoch 30], [iter 121 / 182], [train loss 14.36596]
[epoch 30], [iter 122 / 182], [train loss 14.56526]
[epoch 30], [iter 123 / 182], [train loss 14.48954]
[epoch 30], [iter 124 / 182], [train loss 14.59177]
[epoch 30], [iter 125 / 182], [train loss 14.53667]
[epoch 30], [iter 126 / 182], [train loss 14.59556]
[epoch 30], [iter 127 / 182], [train loss 14.53797]
[epoch 30], [iter 128 / 182], [train loss 14.42439]
[epoch 30], [iter 129 / 182], [train loss 14.48302]
[epoch 30], [iter 130 / 182], [train loss 14.41163]
[epoch 30], [iter 131 / 182], [train loss 14.56384]
[epoch 30], [iter 132 / 182], [train loss 14.45351]
[epoch 30], [iter 133 / 182], [train loss 14.39059]
[epoch 30], [iter 134 / 182], [train loss 14.32216]
[epoch 30], [iter 135 / 182], [train loss 14.37767]
[epoch 30], [iter 136 / 182], [train loss 14.31511]
[epoch 30], [iter 137 / 182], [train loss 14.38090]
[epoch 30], [iter 138 / 182], [train loss 14.51481]
[epoch 30], [iter 139 / 182], [train loss 14.60453]
[epoch 30], [iter 140 / 182], [train loss 14.51285]
[epoch 30], [iter 141 / 182], [train loss 14.62092]
[epoch 30], [iter 142 / 182], [train loss 14.51796]
[epoch 30], [iter 143 / 182], [train loss 14.56977]
[epoch 30], [iter 144 / 182], [train loss 14.85173]
[epoch 30], [iter 145 / 182], [train loss 14.74931]
[epoch 30], [iter 146 / 182], [train loss 14.64830]
[epoch 30], [iter 147 / 182], [train loss 14.57249]
[epoch 30], [iter 148 / 182], [train loss 14.47403]
[epoch 30], [iter 149 / 182], [train loss 14.46919]
[epoch 30], [iter 150 / 182], [train loss 14.55256]
[epoch 30], [iter 151 / 182], [train loss 14.45618]
[epoch 30], [iter 152 / 182], [train loss 14.36221]
[epoch 30], [iter 153 / 182], [train loss 14.59301]
[epoch 30], [iter 154 / 182], [train loss 14.52462]
[epoch 30], [iter 155 / 182], [train loss 14.43091]
[epoch 30], [iter 156 / 182], [train loss 14.33841]
[epoch 30], [iter 157 / 182], [train loss 14.24708]
[epoch 30], [iter 158 / 182], [train loss 14.46720]
[epoch 30], [iter 159 / 182], [train loss 14.49228]
[epoch 30], [iter 160 / 182], [train loss 14.40170]
[epoch 30], [iter 161 / 182], [train loss 14.31225]
[epoch 30], [iter 162 / 182], [train loss 14.22391]
[epoch 30], [iter 163 / 182], [train loss 14.33623]
[epoch 30], [iter 164 / 182], [train loss 14.24881]
[epoch 30], [iter 165 / 182], [train loss 14.16246]
[epoch 30], [iter 166 / 182], [train loss 14.07714]
[epoch 30], [iter 167 / 182], [train loss 14.10332]
[epoch 30], [iter 168 / 182], [train loss 14.04919]
[epoch 30], [iter 169 / 182], [train loss 14.00492]
[epoch 30], [iter 170 / 182], [train loss 13.92254]
[epoch 30], [iter 171 / 182], [train loss 13.84112]
[epoch 30], [iter 172 / 182], [train loss 13.76065]
[epoch 30], [iter 173 / 182], [train loss 13.68111]
[epoch 30], [iter 174 / 182], [train loss 13.67412]
[epoch 30], [iter 175 / 182], [train loss 13.59598]
[epoch 30], [iter 176 / 182], [train loss 13.51873]
[epoch 30], [iter 177 / 182], [train loss 13.44235]
[epoch 30], [iter 178 / 182], [train loss 13.41863]
[epoch 30], [iter 179 / 182], [train loss 13.35066]
[epoch 30], [iter 180 / 182], [train loss 13.27877]
[epoch 30], [iter 181 / 182], [train loss 13.37068]
[epoch 30], [iter 182 / 182], [train loss 13.29721]