I tried doing this by the way and I dont understand what I printed
BATCH_SIZE = 10
EPOCHS = 1
def train(model):
model.train()
for epoch in range(EPOCHS):
for i in tqdm(range(0, len(img_train), BATCH_SIZE)):
batch_img_train = img_train[i:i+BATCH_SIZE].view(-1, 3, 224, 224)
batch_mask_train = mask_train[i:i+BATCH_SIZE].view(-1, 1, 224, 224 )
model.zero_grad()
outputs = model(batch_img_train)
loss = loss_function(outputs, batch_mask_train)
loss.backward
optimizer.step()
return outputs, loss
outputs, loss = train(model)
print(outputs[0])
print(loss)
tensor([[[-0.0091, -0.1961, 0.0587, ..., -0.1641, -0.0139, -0.2890],
[-0.0064, 0.0030, -0.1327, ..., 0.0016, -0.0392, 0.0583],
[ 0.0580, -0.1432, 0.0927, ..., -0.0062, -0.0150, -0.2169],
...,
[-0.0160, -0.0555, -0.0218, ..., -0.0440, 0.0779, 0.0119],
[ 0.0780, -0.2582, 0.3273, ..., -0.1301, -0.0121, -0.3491],
[-0.0095, 0.0300, 0.2434, ..., 0.0927, -0.1081, 0.1011]],
[[ 0.0240, 0.0760, 0.1297, ..., -0.0281, 0.1930, -0.0558],
[ 0.2875, -0.0392, 0.1630, ..., -0.2731, 0.1639, -0.1631],
[ 0.1795, 0.1011, 0.0933, ..., -0.1308, 0.1352, -0.1574],
...,
[ 0.2370, -0.0927, 0.1744, ..., 0.0010, 0.2705, -0.2871],
[ 0.2685, 0.0470, 0.0728, ..., -0.0878, 0.3259, -0.0947],
[ 0.0521, -0.0432, 0.2411, ..., -0.0805, 0.0145, -0.1734]],
[[-0.0826, -0.0991, -0.0454, ..., -0.0914, -0.0570, -0.1069],
[-0.0284, -0.2223, 0.2041, ..., -0.2442, -0.0794, -0.2244],
[-0.1062, -0.1029, 0.2294, ..., -0.0914, -0.1032, 0.0496],
...,
[-0.0181, -0.2399, 0.0967, ..., -0.3608, -0.0362, -0.2599],
[ 0.0174, -0.0861, -0.0526, ..., 0.0006, -0.0621, 0.0562],
[-0.0683, -0.2384, -0.1297, ..., -0.2269, -0.1719, -0.2036]],
...,
[[ 0.0466, 0.0729, 0.1712, ..., 0.0808, -0.0174, 0.0344],
[ 0.0591, 0.1214, 0.2544, ..., -0.1711, 0.0215, -0.1528],
[ 0.0919, 0.0274, -0.1394, ..., 0.0419, 0.1209, 0.0010],
...,
[ 0.1275, -0.0068, 0.1960, ..., -0.0925, 0.0209, -0.0808],
[-0.0907, -0.0289, 0.0956, ..., -0.0043, 0.0141, -0.0482],
[-0.0100, -0.0397, 0.1704, ..., -0.0348, 0.0571, 0.0355]],
[[-0.1661, -0.2054, -0.2219, ..., -0.3749, -0.1241, -0.1909],
[ 0.0185, -0.1433, -0.1410, ..., -0.1159, 0.0940, -0.0041],
[-0.1563, -0.1719, -0.0610, ..., 0.0081, 0.0230, -0.1936],
...,
[-0.0505, -0.0652, -0.1203, ..., 0.0068, 0.1381, -0.0275],
[-0.0941, -0.2070, -0.1704, ..., -0.1199, -0.0481, -0.2115],
[-0.0044, -0.0275, -0.1157, ..., 0.0380, -0.0144, 0.1001]],
[[-0.0658, 0.0374, 0.0149, ..., 0.2753, -0.0432, 0.1743],
[ 0.3474, 0.0585, 0.2438, ..., 0.0770, 0.1662, 0.0813],
[-0.0568, 0.0906, 0.1045, ..., 0.1397, 0.1213, 0.0352],
...,
[ 0.3072, 0.2205, 0.1899, ..., 0.0265, 0.2470, 0.0975],
[-0.1063, 0.1827, 0.0146, ..., 0.1447, -0.0308, 0.0969],
[ 0.1026, 0.1702, 0.2469, ..., 0.0686, 0.1107, 0.1228]]],
grad_fn=<SelectBackward>)
tensor(105.4350, grad_fn=<MseLossBackward>)