import os
import time
import numpy as np
from extra.efficientnet import EfficientNet
from tinygrad.tensor import Tensor
if __name__ == "__main__":
Tensor.default_gpu = os.getenv("GPU") is not None
model = EfficientNet(int(os.getenv("NUM", "0")))
BS = 16
img = np.zeros((BS, 3, 224, 224), dtype=np.float32)
for i in range(32):
print("running batch %d" % i)
st = time.time()
out = model.forward(Tensor(img))
et = time.time()
print("forward %.2f s" % (et - st))
Y = [0] * BS
y = np.zeros((BS, 1000), np.float32)
y[range(y.shape[0]), Y] = -1000.0
y = Tensor(y)
loss = out.logsoftmax().mul(y).mean()
st = time.time()
loss.backward()
et = time.time()
X = db[b'data'].reshape((-1, 3, 32, 32))
Y = np.array(db[b'labels'])
return X, Y
if __name__ == "__main__":
X_train, Y_train = load_cifar()
classes = 10
Tensor.default_gpu = os.getenv("GPU") is not None
TINY = os.getenv("TINY") is not None
TRANSFER = os.getenv("TRANSFER") is not None
if TINY:
model = TinyConvNet(classes)
elif TRANSFER:
model = EfficientNet(int(os.getenv("NUM", "0")), classes, has_se=True)
model.load_weights_from_torch()
else:
model = EfficientNet(int(os.getenv("NUM", "0")), classes, has_se=False)
parameters = get_parameters(model)
print("parameters", len(parameters))
optimizer = optim.Adam(parameters, lr=0.001)
#BS, steps = 16, 32
BS, steps = 64 if TINY else 16, 2048
for i in (t := trange(steps)):
samp = np.random.randint(0, X_train.shape[0], size=(BS))
img = X_train[samp].astype(np.float32)
out = model.forward(Tensor(img).gpu()).cpu()
else:
out = model.forward(Tensor(img))
# if you want to look at the outputs
"""
import matplotlib.pyplot as plt
plt.plot(out.data[0])
plt.show()
"""
return out, retimg
if __name__ == "__main__":
# instantiate my net
model = EfficientNet(int(os.getenv("NUM", "0")))
model.load_weights_from_torch()
if GPU:
[x.gpu_() for x in get_parameters(model)]
# category labels
import ast
lbls = fetch(
"https://gist.githubusercontent.com/yrevar/942d3a0ac09ec9e5eb3a/raw/238f720ff059c1f82f368259d1ca4ffa5dd8f9f5/imagenet1000_clsidx_to_labels.txt"
)
lbls = ast.literal_eval(lbls.decode('utf-8'))
# load image and preprocess
from PIL import Image
url = sys.argv[1]
if url == 'webcam':
import os
import time
import numpy as np
from extra.efficientnet import EfficientNet
from tinygrad.tensor import Tensor
if __name__ == "__main__":
Tensor.default_gpu = os.getenv("GPU") is not None
model = EfficientNet()
BS = 4
img = np.zeros((BS, 3, 224, 224), dtype=np.float32)
st = time.time()
out = model.forward(Tensor(img))
et = time.time()
print("forward %.2f s" % (et - st))
Y = [0] * BS
y = np.zeros((BS, 1000), np.float32)
y[range(y.shape[0]), Y] = -1000.0
y = Tensor(y)
loss = out.logsoftmax().mul(y).mean()
st = time.time()
loss.backward()
et = time.time()
print("backward %.2f s" % (et - st))