Error message
Traceback (most recent call last):
File "pred.py", line 134, in
output = model(data)
Runtime Error: Expected 4-dimensional input for 4-dimensional weight [16, 3, 3, 3], but got 3-dimensional input of size [1, 32, 32] instead.
Prediction code
normalize = transforms.Normalize(mean=[0.4914, 0.4824, 0.4467],
std=[0.2471, 0.2435, 0.2616])
train_set = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
])
model = models.condensenet(args)
model = nn.DataParallel(model)
PATH = "results/savedir/save_models/checkpoint_001.pth.tar"
model.load_state_dict(torch.load(PATH)['state_dict'])
device = torch.device("cpu")
model.eval()
image = Image.open("horse.jpg")
input = train_set(image)
train_loader = torch.utils.data.DataLoader(
input,
batch_size=1,shuffle=True, num_workers=1)
for i, data in enumerate(train_loader):
#input_var = torch.autograd.Variable(data, volatile=True)
#input_var = input_var.view(1, 3, 32,32)
**output = model(data)
topk=(1,5)
maxk = max(topk)
_, pred = output.topk(maxk, 1, True, True)
Am getting this error when am trying to predict on a single image
Image shape/size error message
Link to saved model
Training code repository
Plz uncomment this line #input_var = input_var.view(1, 3, 32,32) so that your input dimension is 4.
I assume that your no. of input channels are 3 if its one then use input_var = input_var.view(1, 1, 32,32) if gray scale
Instead of doing the for loop and train_loader, solved this by just passing the input directly into the model. like this
input = train_set(image)
input = input.unsqueeze(0)
model.eval()
output = model(input)
More details can be found here link
Related
I am new to transformer based models. I am trying to fine-tune the following model (https://huggingface.co/Chramer/remote-sensing-distilbert-cased) on my dataset. The code:
enter image description here
and I got the following error:
enter image description here
I will be thankful if anyone could help.
The preprocessing steps I followed:
input_ids_t = []
attention_masks_t = []
for sent in df_train['text_a']:
encoded_dict = tokenizer.encode_plus(
sent,
add_special_tokens = True,
max_length = 128,
pad_to_max_length = True,
return_attention_mask = True,
return_tensors = 'tf',
)
input_ids_t.append(encoded_dict['input_ids'])
attention_masks_t.append(encoded_dict['attention_mask'])
# Convert the lists into tensors.
input_ids_t = tf.concat(input_ids_t, axis=0)
attention_masks_t = tf.concat(attention_masks_t, axis=0)
labels_t = np.asarray(df_train['label'])
and i did the same for testing data. Then:
train_data = tf.data.Dataset.from_tensor_slices((input_ids_t,attention_masks_t,labels_t))
and the same for testing data
It sounds like you are feeding the transformer_model 1 input instead of 3. Try removing the square brackets around transformer_model([input_ids, input_mask, segment_ids])[0] so that it reads transformer_model(input_ids, input_mask, segment_ids)[0]. That way, the function will have 3 arguments and not just 1.
I'have implemented a keras lstm network in R and I can train it and use correctly the fit function. But when I use "predict" function, I meet following errors:
pred <- base_model %>% predict(matchsetarray)
WARNING:tensorflow:Model was constructed with shape (96, 2, 26) for input KerasTensor(type_spec=TensorSpec(shape=(96, 2, 26), dtype=tf.float32, name='lstm_3_input'), name='lstm_3_input', description="created by layer 'lstm_3_input'"), but it was called on an input with incompatible shape (32, 2, 26).
Error in py_call_impl(callable, dots$args, dots$keywords) :
ValueError: in user code:
File "C:\Users\Utente\AppData\Local\R-MINI~1\envs\R-RETI~1\lib\site-packages\keras\engine\training.py", line 1801, in predict_function *
return step_function(self, iterator)
File "C:\Users\Utente\AppData\Local\R-MINI~1\envs\R-RETI~1\lib\site-packages\keras\engine\training.py", line 1790, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\Users\Utente\AppData\Local\R-MINI~1\envs\R-RETI~1\lib\site-packages\keras\engine\training.py", line 1783, in run_step **
outputs = model.predict_step(data)
File "C:\Users\Utente\AppData\Local\R-MINI~1\envs\R-RETI~1\lib\site-packages\keras\engine\training.py", line 1751, in predict_step
return self(x, training=False)
File "C:\Users\Utente\AppData\Local\R-MINI~1\envs\R-RETI~1\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\
However the dimension of predict input is (96,2,26), but "predict" consider the input "matchsetarray" of dimension (32, 2, 26). Could I force predict to read teh correct format?
I tryed to verify the dimension of input "matchsetarray":
dim(matchsetarray)
[1] 96 2 26
It's the correct dimension expected by "predict" function.
I try to run the MAC network (https://github.com/stanfordnlp/mac-network/tree/gqa) with Auto Mixed Precision.
def addOptimizerOp(self):
with tf.variable_scope("trainAddOptimizer"):
self.globalStep = tf.Variable(0, dtype = tf.int32, trainable = False, name = "globalStep") # init to 0 every run?
optimizer = tf.train.AdamOptimizer(learning_rate = self.lr)
optimizer = tf.train.experimental.enable_mixed_precision_graph_rewrite(optimizer)
if config.subsetOpt:
self.subsetOptimizer = tf.train.AdamOptimizer(learning_rate = self.lr * config.subsetOptMult)
return optimizer
In the first epoch, training is ok. However, when the model run evaluation on the validation set, I got this error.
Training epoch 1...
2019-08-05 14:51:13.625899: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1767] Running auto_mixed_precision graph optimizer
2019-08-05 14:51:13.709959: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1723] Converted 1504/6920 nodes to float16 precision using 150 cast(s) to float16 (excluding Const and Variable casts)
2019-08-05 14:51:16.930248: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcublas.so.10.0
2019-08-05 14:51:17.331687: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library libcudnn.so.7
2019-08-05 14:51:29.378905: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1767] Running auto_mixed_precision graph optimizer
2019-08-05 14:51:29.380633: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1241] No whitelist ops found, nothing to do
eb 1, 10000,(160010 / 943000), t = 0.12 (0.00+0.11), lr 0.0003, l = 2.8493, a = 0.4250, avL = 2.5323, avA = 0.4188, g = 3.7617, emL = 2.3097, emA = 0.4119; gqaExperiment
Restoring EMA weights
2019-08-05 14:51:31.132804: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1767] Running auto_mixed_precision graph optimizer
2019-08-05 14:51:31.136122: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1241] No whitelist ops found, nothing to do
2019-08-05 14:51:32.322369: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1767] Running auto_mixed_precision graph optimizer
2019-08-05 14:51:32.341609: I tensorflow/core/grappler/optimizers/auto_mixed_precision.cc:1723] Converted 661/1848 nodes to float16 precision using 38 cast(s) to float16 (excluding Const and Variable casts)
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1356, in _do_call
return fn(*args)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1341, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1429, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: TensorArray dtype is float but Op is trying to write dtype half.
[[{{node macModel/tower0/encoder/birnnLayer/bidirectional_rnn/fw/fw/while/TensorArrayWrite/TensorArrayWriteV3}}]]
[[macModel/tower0/MACnetwork/MACCell_3/write/inter2attselfAttention/Softmax/_1661]]
(1) Invalid argument: TensorArray dtype is float but Op is trying to write dtype half.
[[{{node macModel/tower0/encoder/birnnLayer/bidirectional_rnn/fw/fw/while/TensorArrayWrite/TensorArrayWriteV3}}]]
0 successful operations.
0 derived errors ignored.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "main.py", line 866, in <module>
main()
File "main.py", line 728, in main
evalRes = runEvaluation(sess, model, data["main"], dataOps, epoch, getPreds = getPreds, prevRes = evalRes)
File "main.py", line 248, in runEvaluation
minLoss = prevRes["train"]["minLoss"] if prevRes else float("inf"))
File "main.py", line 594, in runEpoch
res = model.runBatch(sess, batch, imagesBatch, train, getPreds, getAtt)
File "/content/model.py", line 948, in runBatch
feed_dict = feed)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 950, in run
run_metadata_ptr)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1173, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1350, in _do_run
run_metadata)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py", line 1370, in _do_call
raise type(e)(node_def, op, message)
I think the errors may come from not turning off the auto mixed precision on evaluation time or using the same session and model for train and evaluation. I tried "tf.train.experimental.disable_mixed_precision_graph_rewrite()" but I do not know how to use it in the right way.
How can I fix it? Thanks all.
def main():
with open(config.configFile(), "a+") as outFile:
json.dump(vars(config), outFile)
# set gpus
if config.gpus != "":
config.gpusNum = len(config.gpus.split(","))
os.environ["CUDA_VISIBLE_DEVICES"] = config.gpus
tf.logging.set_verbosity(tf.logging.ERROR)
# process data
print(bold("Preprocess data..."))
start = time.time()
preprocessor = Preprocesser()
data, embeddings, answerDict, questionDict = preprocessor.preprocessData()
print("took {} seconds".format(bcolored("{:.2f}".format(time.time() - start), "blue")))
nextElement = None
dataOps = None
# build model
print(bold("Building model..."))
start = time.time()
model = MACnet(embeddings, answerDict, questionDict, nextElement)
print("took {} seconds".format(bcolored("{:.2f}".format(time.time() - start), "blue")))
# initializer
init = tf.global_variables_initializer()
# savers
savers = setSavers(model)
saver, emaSaver = savers["saver"], savers["emaSaver"]
# sessionConfig
sessionConfig = setSession()
with tf.Session(config = sessionConfig) as sess:
# ensure no more ops are added after model is built
sess.graph.finalize()
# restore / initialize weights, initialize epoch variable
epoch = loadWeights(sess, saver, init)
trainRes, evalRes = None, None
if config.train:
start0 = time.time()
bestEpoch = epoch
bestRes = None
prevRes = None
# epoch in [restored + 1, epochs]
for epoch in range(config.restoreEpoch + 1, config.epochs + 1):
print(bcolored("Training epoch {}...".format(epoch), "green"))
start = time.time()
# train
# calle = lambda: model.runEpoch(), collectRuntimeStats, writer
trainingData, alterData = chooseTrainingData(data)
trainRes = runEpoch(sess, model, trainingData, dataOps, train = True, epoch = epoch,
saver = saver, alterData = alterData,
maxAcc = trainRes["maxAcc"] if trainRes else 0.0,
minLoss = trainRes["minLoss"] if trainRes else float("inf"),)
# save weights
saver.save(sess, config.weightsFile(epoch))
if config.saveSubset:
subsetSaver.save(sess, config.subsetWeightsFile(epoch))
# load EMA weights
if config.useEMA:
print(bold("Restoring EMA weights"))
emaSaver.restore(sess, config.weightsFile(epoch))
# evaluation
getPreds = config.getPreds or (config.analysisType != "")
evalRes = runEvaluation(sess, model, data["main"], dataOps, epoch, getPreds = getPreds, prevRes = evalRes)
extraEvalRes = runEvaluation(sess, model, data["extra"], dataOps, epoch,
evalTrain = not config.extraVal, getPreds = getPreds)
# restore standard weights
if config.useEMA:
print(bold("Restoring standard weights"))
saver.restore(sess, config.weightsFile(epoch))
print("")
epochTime = time.time() - start
print("took {:.2f} seconds".format(epochTime))
# print results
printDatasetResults(trainRes, evalRes, extraEvalRes)
I am working on a deep learning problem. I am solving it using pytorch. I have two GPU's which are on the same machine (16273MiB,12193MiB). I want to use both the GPU's for my training (video dataset).
I get a warning:
There is an imbalance between your GPUs. You may want to exclude GPU 1 which
has less than 75% of the memory or cores of GPU 0. You can do so by setting
the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
environment variable.
warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
I also get an error:
raise TypeError('Broadcast function not implemented for CPU tensors')
TypeError: Broadcast function not implemented for CPU tensors
if __name__ == '__main__':
opt.scales = [opt.initial_scale]
for i in range(1, opt.n_scales):
opt.scales.append(opt.scales[-1] * opt.scale_step)
opt.arch = '{}-{}'.format(opt.model, opt.model_depth)
opt.mean = get_mean(opt.norm_value)
opt.std = get_std(opt.norm_value)
print("opt",opt)
with open(os.path.join(opt.result_path, 'opts.json'), 'w') as opt_file:
json.dump(vars(opt), opt_file)
torch.manual_seed(opt.manual_seed)
model, parameters = generate_model(opt)
#print(model)
pytorch_total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
print("Total number of trainable parameters: ", pytorch_total_params)
# Define Class weights
if opt.weighted:
print("Weighted Loss is created")
if opt.n_finetune_classes == 2:
weight = torch.tensor([1.0, 3.0])
else:
weight = torch.ones(opt.n_finetune_classes)
else:
weight = None
criterion = nn.CrossEntropyLoss()
if not opt.no_cuda:
criterion = nn.DataParallel(criterion.cuda())
if opt.no_mean_norm and not opt.std_norm:
norm_method = Normalize([0, 0, 0], [1, 1, 1])
elif not opt.std_norm:
norm_method = Normalize(opt.mean, [1, 1, 1])
else:
norm_method = Normalize(opt.mean, opt.std)
train_loader = torch.utils.data.DataLoader(
training_data,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.n_threads,
pin_memory=True)
train_logger = Logger(
os.path.join(opt.result_path, 'train.log'),
['epoch', 'loss', 'acc', 'precision','recall','lr'])
train_batch_logger = Logger(
os.path.join(opt.result_path, 'train_batch.log'),
['epoch', 'batch', 'iter', 'loss', 'acc', 'precision', 'recall', 'lr'])
if opt.nesterov:
dampening = 0
else:
dampening = opt.dampening
optimizer = optim.SGD(
parameters,
lr=opt.learning_rate,
momentum=opt.momentum,
dampening=dampening,
weight_decay=opt.weight_decay,
nesterov=opt.nesterov)
# scheduler = lr_scheduler.ReduceLROnPlateau(
# optimizer, 'min', patience=opt.lr_patience)
if not opt.no_val:
spatial_transform = Compose([
Scale(opt.sample_size),
CenterCrop(opt.sample_size),
ToTensor(opt.norm_value), norm_method
])
print('run')
for i in range(opt.begin_epoch, opt.n_epochs + 1):
if not opt.no_train:
adjust_learning_rate(optimizer, i, opt.lr_steps)
train_epoch(i, train_loader, model, criterion, optimizer, opt,
train_logger, train_batch_logger)
I have also made changes in my train file:
model = nn.DataParallel(model(),device_ids=[0,1]).cuda()
outputs = model(inputs)
It does not seem to work properly and is giving error. Please advice, I am new to pytorch.
Thanks
As mentioned in this link, you have to do model.cuda() before passing it to nn.DataParallel.
net = nn.DataParallel(model.cuda(), device_ids=[0,1])
https://github.com/pytorch/pytorch/issues/17065
I am trying to subject a one image array to STN using code from https://github.com/kevinzakka/spatial-transformer-network :
def STNfn(x):
import tensorflow as tf
print(x.shape)
B,W,H,C = x.shape
# identity transform
initial = np.array([[1., 0, 0], [0, 1., 0]])
initial = initial.astype('float32').flatten()
# localization network
n_fc = 6
W_fc1 = tf.Variable(tf.zeros([H*W*C, n_fc]), name='W_fc1')
b_fc1 = tf.Variable(initial_value=initial, name='b_fc1')
h_fc1 = tf.matmul(tf.zeros([B, H*W*C]), W_fc1) + b_fc1
# spatial transformer layer
from stn import spatial_transformer_network as transformer
h_trans = transformer(x, h_fc1)
return h_trans
fname = 'testimage.jpg'
img = plt.imread(fname)
img = STNfn(np.array([img]))
However, I am getting following error:
TypeError: Input 'y' of 'Mul' Op has type uint8
that does not match type float32 of argument 'x'.
I have tried to replace float32 with np.uint8, but it does not help.
Where is the problem and how can it be solved?
n_fc = 6 has to be a float32 maybe? Not familar with Python, in Java it is like 6.0f for float and just 6 is integer.