{"metadata":{"colab":{"provenance":

[],"authorship_tag":"ABX9TyMa4luEu5TX6eIwRsVTFquF"},"kernelspec":
{"name":"python3","display_name":"Python 3","language":"python"},"language_info":
{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":
{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"py
thon","file_extension":".py"},"kaggle":
{"accelerator":"nvidiaTeslaT4","dataSources":
[{"sourceId":9563184,"sourceType":"datasetVersion","datasetId":5828021}],"dockerIma
geVersionId":30787,"isInternetEnabled":true,"language":"python","sourceType":"noteb
ook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":
[{"cell_type":"raw","source":"import torch\nimport torch.nn as nn\nimport
torch.nn.functional as F\nfrom torch.autograd import Variable\nfrom
torch.utils.data import DataLoader\nfrom torchvision import transforms\nfrom
torchvision import datasets\n#import resnet50\nfrom torchvision.models import
resnet18,resnet50,resnet101\nimport matplotlib.pyplot as plt\nimport numpy as np\
nimport matplotlib.pyplot as plt\nimport skimage\nimport random","metadata":
{"id":"xyDnWcQnfD6a","execution":{"iopub.status.busy":"2024-10-
06T23:22:58.532104Z","iopub.execute_input":"2024-10-
06T23:22:58.532514Z","iopub.status.idle":"2024-10-
06T23:23:03.008468Z","shell.execute_reply.started":"2024-10-
06T23:22:58.532478Z","shell.execute_reply":"2024-10-06T23:23:03.007348Z"}}},
{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport
torch.nn.functional as F\nfrom torch.autograd import Variable\nfrom
torch.utils.data import DataLoader\nfrom torchvision import transforms\nfrom
torchvision import datasets\n#import resnet50\nfrom torchvision.models import
resnet18,resnet50,resnet101\nimport matplotlib.pyplot as plt\nimport numpy as np\
nimport matplotlib.pyplot as plt\nimport skimage\nimport random","metadata":
{"execution":{"iopub.status.busy":"2024-10-
07T18:36:29.490517Z","iopub.execute_input":"2024-10-
07T18:36:29.491795Z","iopub.status.idle":"2024-10-
07T18:36:29.498469Z","shell.execute_reply.started":"2024-10-
07T18:36:29.491745Z","shell.execute_reply":"2024-10-
07T18:36:29.497116Z"},"trusted":true},"execution_count":9,"outputs":[]},
{"cell_type":"markdown","source":"","metadata":{"id":"NPp-3gjFpA0q"}},
{"cell_type":"code","source":"#create
images\nmonkee=skimage.io.imread('/kaggle/input/imagenmonkee/fae6202d-2a8b-40e3-
8d05-19f46ba7b537.ce308afc0ee1b59229142849913da8f1.jpeg')\
nmonkee=skimage.transform.resize(monkee,(250,250))\nimg=monkee\npreprocess =
transforms.Compose([\n transforms.ToPILImage(),\n transforms.Resize(256),\n
transforms.CenterCrop(224),\n transforms.ToTensor(),\n
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n])\
n#create 1500x1500 canvas\ncanvas=np.zeros((1500,1500,3))\nx=750-monkee.shape[0]/2\
nresnetimages=[]\nys=[]\nfor i in range(3):\n y=random.randint(0,1000)\n
canvas[int(y):int(y)+monkee.shape[0],int(x):int(x)+monkee.shape[1]]=monkee\n
yinfivesec=y+(1/2)*9.8*5**2\n ys.append(yinfivesec)\n
resnetimages.append(preprocess(canvas))\n canvas=np.zeros((1500,1500,3))\n\n\n\
n\nplt.imshow(canvas)","metadata":{"id":"eEaP2EL-oBHq","colab":
{"base_uri":"https://localhost:8080/","height":452},"executionInfo":
{"status":"ok","timestamp":1728255917927,"user_tz":300,"elapsed":3765,"user":
{"displayName":"DAVID SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"}},"outputId":"a46c42fe-b2fd-4e1a-df59-
e92043d17de6","execution":{"iopub.status.busy":"2024-10-
07T18:36:29.500507Z","iopub.execute_input":"2024-10-
07T18:36:29.500838Z","iopub.status.idle":"2024-10-
07T18:36:32.811426Z","shell.execute_reply.started":"2024-10-
07T18:36:29.500803Z","shell.execute_reply":"2024-10-
07T18:36:32.810011Z"},"trusted":true},"execution_count":10,"outputs":
[{"execution_count":10,"output_type":"execute_result","data":{"text/
plain":"<matplotlib.image.AxesImage at 0x7bfa4e2fffa0>"},"metadata":{}},
{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1
Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAbIAAAGiCAYAAACCpUOHAAAAOXRFWHRTb2Z0d2F
yZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/
xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAoPUlEQVR4nO3df3DU9Z3H8deGkCUx7iaA2SWYYNoyUIXSaD
S3ivYPMgSPUVud9ppJKUeZMlg8wToUMw7UXscmhTt/
3SlqZ06ZqZWWGcHKiE6aUCLTGCAEELCRGymk6CZXYnaDQkjY9/3R43ssRgllQ/
JJn4+Z94z5ft673897SPKaTT5ufGZmAgDAUWlDvQEAAC4FQQYAcBpBBgBwGkEGAHAaQQYAcBpBBgBwGkEGA
HAaQQYAcBpBBgBwGkEGAHDasA6yp59+Wtdcc43GjBmj0tJS7dixY6i3BAAYZoZtkP3617/WD3/4Q/34xz/
W7t27NWPGDJWXl6ujo2OotwYAGEZ8w/VNg0tLS3XjjTfqP//zPyVJiURCBQUF+pd/
+Rc99NBDQ7w7AMBwkT7UG+jP6dOn1dzcrKqqKu9aWlqaysrK1NjY2O9jenp61NPT432cSCTU2dmpcePGyef
zDfqeAQCpY2bq7u5Wfn6+0tI+/4eHwzLI/vKXv+jMmTMKhUJJ10OhkP74xz/2+5jq6mr95Cc/
uRzbAwBcJm1tbbr66qs/t2fY/
o7sYlVVVSkWi3l19OjRod4SAOASXXnllRfsGZavyMaPH69Ro0apvb096Xp7e7vC4XC/j/H7/fL7/
ZdjewCAy2Qgvxoalq/IMjIydMMNN6iurs67lkgkVFdXp0gkMoQ7AwAMN8PyFZkk/
fCHP9T8+fNVUlKim266SU888YQ+/vhjLViwYKi3BgAYRoZtkP3TP/2T/ud//
kerVq1SNBrVV7/6Vb3xxhufOgACAPj7Nmz/P7JLFY/
HFQwGh3obAIBLEIvFFAgEPrdnWP6ODACAgSLIAABOI8gAAE4jyAAATiPIAABOI8gAAE4jyAAATiPIAABOI8
gAAE4jyAAATiPIAABOI8gAAE4jyAAATiPIAABOI8gAAE4jyAAATiPIAABOI8gAAE4jyAAATiPIAABOI8gAA
E4jyAAATiPIAABOI8gAAE4jyAAATiPIAABOI8gAAE4jyAAATiPIAABOI8gAAE4jyAAATiPIAABOI8gAAE4j
yAAATiPIAABOI8gAAE4jyAAATiPIAABOS3mQVVdX68Ybb9SVV16pvLw8ff3rX1dra2tSz6lTp7RkyRKNGzd
O2dnZuueee9Te3p7Uc/ToUc2dO1dZWVnKy8vT8uXL1dfXl+rtAgAcl/
Ig27Ztm5YsWaK3335btbW16u3t1ezZs/Xxxx97PQ888IBee+01bdiwQdu2bdMHH3ygu+++21s/
c+aM5s6dq9OnT+sPf/iD1q1bpxdffFGrVq1K9XYBAK6zQdbR0WGSbNu2bWZm1tXVZaNHj7YNGzZ4Pe++
+65JssbGRjMze/311y0tLc2i0ajXs3btWgsEAtbT0zOg+8ZiMZNEURRFOVyxWOyC3+8H/
XdksVhMkjR27FhJUnNzs3p7e1VWVub1TJ06VYWFhWpsbJQkNTY2avr06QqFQl5PeXm54vG4Dhw40O99enp6
FI/
HkwoAMPINapAlEgktW7ZMt9xyi6ZNmyZJikajysjIUE5OTlJvKBRSNBr1es4NsbPrZ9f6U11drWAw6FVBQU
GKpwEADEeDGmRLlizR/v37tX79+sG8jSSpqqpKsVjMq7a2tkG/
JwBg6KUP1hPfd9992rx5sxoaGnT11Vd718PhsE6fPq2urq6kV2Xt7e0Kh8Nez44dO5Ke7+ypxrM95/P7/
fL7/
SmeAgAw3KX8FZmZ6b777tPGjRtVX1+voqKipPUbbrhBo0ePVl1dnXettbVVR48eVSQSkSRFIhG988476ujo
8Hpqa2sVCAR07bXXpnrLAACXXcQBxAG59957LRgM2u9//3v78MMPvfrkk0+8nsWLF1thYaHV19fbrl27LBK
JWCQS8db7+vps2rRpNnv2bNuzZ4+98cYbdtVVV1lVVdWA98GpRYqiKPdrIKcWUx5kn7WZF154wes5efKk/
eAHP7Dc3FzLysqyb3zjG/bhhx8mPc+f/vQnu/322y0zM9PGjx9vDz74oPX29g54HwQZRVGU+zWQIPP9X/
iMOPF4XMFgcKi3AQC4BLFYTIFA4HN7eK9FAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAg
NMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMI
MgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgC
A0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wY9yGpqauTz+bRs2TLv2qlTp7RkyRKNGzdO2dnZuu
eee9Te3p70uKNHj2ru3LnKyspSXl6eli9frr6+vsHeLgDAMYMaZDt37tRzzz2nr3zlK0nXH3jgAb322mvas
GGDtm3bpg8++EB33323t37mzBnNnTtXp0+f1h/
+8AetW7dOL774olatWjWY2wUAuMgGSXd3t02ePNlqa2vta1/7mi1dutTMzLq6umz06NG2YcMGr/
fdd981SdbY2GhmZq+//
rqlpaVZNBr1etauXWuBQMB6enr6vd+pU6csFot51dbWZpIoiqIohysWi10wbwbtFdmSJUs0d+5clZWVJV1v
bm5Wb29v0vWpU6eqsLBQjY2NkqTGxkZNnz5doVDI6ykvL1c8HteBAwf6vV91dbWCwaBXBQUFgzAVAGC4GZQ
gW79+vXbv3q3q6upPrUWjUWVkZCgnJyfpeigUUjQa9XrODbGz62fX+lNVVaVYLOZVW1tbCiYBAAx36al+wr
a2Ni1dulS1tbUaM2ZMqp/+M/n9fvn9/st2PwDA8JDyV2TNzc3q6OjQ9ddfr/
T0dKWnp2vbtm166qmnlJ6erlAopNOnT6urqyvpce3t7QqHw5KkcDj8qVOMZz8+2wMAgDQIQTZr1iy988472
rNnj1clJSWqrKz0/
nv06NGqq6vzHtPa2qqjR48qEolIkiKRiN555x11dHR4PbW1tQoEArr22mtTvWUAgMsu4WDigJ17atHMbPHi
xVZYWGj19fW2a9cui0QiFolEvPW+vj6bNm2azZ492/bs2WNvvPGGXXXVVVZVVTXge8ZisSE/
bUNRFEVdWg3k1GLKf0c2EI8//rjS0tJ0zz33qKenR+Xl5XrmmWe89VGjRmnz5s269957FYlEdMUVV2j+/
Pn613/916HYLgBgGPOZmQ31JgZDPB5XMBgc6m0AAC5BLBZTIBD43B7eaxEA4DSCDADgNIIMAOA0ggwA4DSC
DADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDAD
gNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNI
IMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgtEEJsmPHjuk73/
mOxo0bp8zMTE2fPl27du3y1s1Mq1at0oQJE5SZmamysjIdOnQo6Tk6OztVWVmpQCCgnJwcLVy4UCdOnBiM7
QIAHJbyIPvoo490yy23aPTo0dqyZYsOHjyof//
3f1dubq7Xs3r1aj311FN69tln1dTUpCuuuELl5eU6deqU11NZWakDBw6otrZWmzdvVkNDgxYtWpTq7QIAXG
cptmLFCps5c+ZnricSCQuHw7ZmzRrvWldXl/
n9fnv55ZfNzOzgwYMmyXbu3On1bNmyxXw+nx07dmxA+4jFYiaJoiiKcrhisdgFv9+n/
BXZb3/7W5WUlOib3/ym8vLyVFxcrF/
84hfe+uHDhxWNRlVWVuZdCwaDKi0tVWNjoySpsbFROTk5Kikp8XrKysqUlpampqamfu/
b09OjeDyeVACAkS/lQfb+++9r7dq1mjx5st58803de++9uv/+
+7Vu3TpJUjQalSSFQqGkx4VCIW8tGo0qLy8vaT09PV1jx471es5XXV2tYDDoVUFBQapHAwAMQykPskQioeu
vv14/+9nPVFxcrEWLFun73/++nn322VTfKklVVZVisZhXbW1tg3o/
AMDwkPIgmzBhgq699tqka1/+8pd19OhRSVI4HJYktbe3J/W0t7d7a+FwWB0dHUnrfX196uzs9HrO5/
f7FQgEkgoAMPKlPMhuueUWtba2Jl177733NGnSJElSUVGRwuGw6urqvPV4PK6mpiZFIhFJUiQSUVdXl5qbm
72e+vp6JRIJlZaWpnrLAACXDegI4EXYsWOHpaen26OPPmqHDh2yl156ybKysuyXv/
yl11NTU2M5OTn26quv2r59+
+yuu+6yoqIiO3nypNczZ84cKy4utqamJtu+fbtNnjzZKioqBrwPTi1SFEW5XwM5tZjyIDMze+2112zatGnm
9/tt6tSp9vzzzyetJxIJW7lypYVCIfP7/TZr1ixrbW1N6jl+/
LhVVFRYdna2BQIBW7BggXV3dw94DwQZRVGU+zWQIPOZmWkEisfjCgaDQ70NAMAliMViFzzzwHstAgCcRpAB
AJxGkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJx
GkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJxGkA
EAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJxGkAEAnEaQAQCcRpABAJyW8iA7c
+aMVq5cqaKiImVmZuqLX/
yifvrTn8rMvB4z06pVqzRhwgRlZmaqrKxMhw4dSnqezs5OVVZWKhAIKCcnRwsXLtSJEydSvV0AgOssxR599
FEbN26cbd682Q4fPmwbNmyw7Oxse/LJJ72empoaCwaDtmnTJtu7d6/
deeedVlRUZCdPnvR65syZYzNmzLC3337b3nrrLfvSl75kFRUVA95HLBYzSRRFUZTDFYvFLvj9PuVBNnfuXP
ve976XdO3uu++2yspKMzNLJBIWDodtzZo13npXV5f5/
X57+eWXzczs4MGDJsl27tzp9WzZssV8Pp8dO3ZsQPsgyCiKotyvgQRZyn+0ePPNN6uurk7vvfeeJGnv3r3a
vn27br/9dknS4cOHFY1GVVZW5j0mGAyqtLRUjY2NkqTGxkbl5OSopKTE6ykrK1NaWpqampr6vW9PT4/
i8XhSAQBGvvRUP+FDDz2keDyuqVOnatSoUTpz5oweffRRVVZWSpKi0agkKRQKJT0uFAp5a9FoVHl5eckbTU
/X2LFjvZ7zVVdX6yc/+UmqxwEADHMpf0X2m9/8Ri+99JJ+9atfaffu3Vq3bp3+7d/
+TevWrUv1rZJUVVUpFot51dbWNqj3AwAMDyl/
RbZ8+XI99NBD+va3vy1Jmj59uo4cOaLq6mrNnz9f4XBYktTe3q4JEyZ4j2tvb9dXv/pVSVI4HFZHR0fS8/
b19amzs9N7/Pn8fr/8fn+qxwEADHMpf0X2ySefKC0t+WlHjRqlRCIhSSoqKlI4HFZdXZ23Ho/
H1dTUpEgkIkmKRCLq6upSc3Oz11NfX69EIqHS0tJUbxkA4LIBHQG8CPPnz7eJEyd6x+9feeUVGz9+vP3oRz
/yempqaiwnJ8deffVV27dvn9111139Hr8vLi62pqYm2759u02ePJnj9xRFUX9n
NSTH7+PxuC1dutQKCwttzJgx9oUvfMEefvhh6+np8XoSiYStXLnSQqGQ+f1+mzVrlrW2tiY9z/
Hjx62iosKys7MtEAjYggULrLu7e8D7IMgoiqLcr4EEmc/
snLfcGEHi8biCweBQbwMAcAlisZgCgcDn9vBeiwAApxFkAACnEWQAAKcRZAAApxFkAACnEWQAAKcRZAAApx
FkAACnEWQAAKcRZAAApxFkAACnEWQAAKcRZAAApxFkAACnEWQAAKcRZAAApxFkAACnEWQAAKcRZAAApxFkA
ACnEWQAAKcRZAAApxFkAACnEWQAAKcRZAAApxFkAACnEWQAAKcRZAAApxFkAACnEWQAAKcRZAAApxFkAACn
EWQAAKcRZAAApxFkAACnEWQAAKcRZAAApxFkAACnXXSQNTQ06I477lB+fr58Pp82bdqUtG5mWrVqlSZMmKD
MzEyVlZXp0KFDST2dnZ2qrKxUIBBQTk6OFi5cqBMnTiT17Nu3T7feeqvGjBmjgoICrV69+uKnAwCMeBcdZB
9//LFmzJihp59+ut/
11atX66mnntKzzz6rpqYmXXHFFSovL9epU6e8nsrKSh04cEC1tbXavHmzGhoatGjRIm89Ho9r9uzZmjRpkp
qbm7VmzRo98sgjev755/+GEQEAI5pdAkm2ceNG7+NEImHhcNjWrFnjXevq6jK/328vv/
yymZkdPHjQJNnOnTu9ni1btpjP57Njx46Zmdkzzzxjubm51tPT4/
WsWLHCpkyZMuC9xWIxk0RRFEU5XLFY7ILf71P6O7LDhw8rGo2qrKzMuxYMBlVaWqrGxkZJUmNjo3JyclRSU
uL1lJWVKS0tTU1NTV7PbbfdpoyMDK+nvLxcra2t+uijj/
q9d09Pj+LxeFIBAEa+lAZZNBqVJIVCoaTroVDIW4tGo8rLy0taT09P19ixY5N6+nuOc+9xvurqagWDQa8KC
goufSAAwLA3Yk4tVlVVKRaLedXW1jbUWwIAXAYpDbJwOCxJam9vT7re3t7urYXDYXV0dCSt9/
X1qbOzM6mnv+c49x7n8/
v9CgQCSQUAGPlSGmRFRUUKh8Oqq6vzrsXjcTU1NSkSiUiSIpGIurq61Nzc7PXU19crkUiotLTU62loaFBvb
6/XU1tbqylTpig3NzeVWwYAuG7AxwD/
T3d3t7W0tFhLS4tJsscee8xaWlrsyJEjZmZWU1NjOTk59uqrr9q+ffvsrrvusqKiIjt58qT3HHPmzLHi4mJ
ramqy7du32+TJk62iosJb7+rqslAoZPPmzbP9+/
fb+vXrLSsry5577rkB75NTixRFUe7XQE4tXnSQbd26td+bzZ8/38z+egR/5cqVFgqFzO/
326xZs6y1tTXpOY4fP24VFRWWnZ1tgUDAFixYYN3d3Uk9e/futZkzZ5rf77eJEydaTU3NRe2TIKMoinK/
BhJkPjMzjUDxeFzBYHCotwEAuASxWOyCZx5GzKlFAMDfJ4IMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDAD
gNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNI
IMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMA
OA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4LSLDrKGhgbdcccdys/Pl8/
n06ZNm7y13t5erVixQtOnT9cVV1yh/
Px8ffe739UHH3yQ9BydnZ2qrKxUIBBQTk6OFi5cqBMnTiT17Nu3T7feeqvGjBmjgoICrV69+m+bEAAwol10
kH388ceaMWOGnn766U+tffLJJ9q9e7dWrlyp3bt365VXXlFra6vuvPPOpL7KykodOHBAtbW12rx5sxoaGrR
o0SJvPR6Pa/bs2Zo0aZKam5u1Zs0aPfLII3r++ef/hhEBACOaXQJJtnHjxs/
t2bFjh0myI0eOmJnZwYMHTZLt3LnT69myZYv5fD47duyYmZk988wzlpubaz09PV7PihUrbMqUKZ95n1OnTl
ksFvOqra3NJFEURVEOVywWu2AWDfrvyGKxmHw+n3JyciRJjY2NysnJUUlJiddTVlamtLQ0NTU1eT233XabM
jIyvJ7y8nK1trbqo48+6vc+1dXVCgaDXhUUFAzeUACAYWNQg+zUqVNasWKFKioqFAgEJEnRaFR5eXlJfenp
6Ro7dqyi0ajXEwqFknrOfny253xVVVWKxWJetbW1pXocAMAwlD5YT9zb26tvfetbMjOtXbt2sG7j8fv98vv
9g34fAMDwMihBdjbEjhw5ovr6eu/VmCSFw2F1dHQk9ff19amzs1PhcNjraW9vT+o5+/
HZHgAApEH40eLZEDt06JB+97vfady4cUnrkUhEXV1dam5u9q7V19crkUiotLTU62loaFBvb6/
XU1tbqylTpig3NzfVWwYAuOyCx0HO093dbS0tLdbS0mKS7LHHHrOWlhY7cuSInT592u688067+uqrbc+ePf
bhhx96de4JxDlz5lhxcbE1NTXZ9u3bbfLkyVZRUeGtd3V1WSgUsnnz5tn+/ftt/
fr1lpWVZc8999yA9xmLxYb8tA1FURR1aTWQU4sXHWRbt27t92bz58+3w4cPf+Zmtm7d6j3H8ePHraKiwrKz
sy0QCNiCBQusu7s76T579+61mTNnmt/
vt4kTJ1pNTc1F7ZMgoyiKcr8GEmQ+MzONQPF4XMFgcKi3AQC4BLFYLOmcRX94r0UAgNMIMgCA0wgyAIDTCD
IAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAg
NMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMI
MgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0wgyAIDTCDIAgNMIMgCA0y46yBoaGnTHHXcoPz9
fPp9PmzZt+szexYsXy+fz6Yknnki63tnZqcrKSgUCAeXk5GjhwoU6ceJEUs+
+fft06623asyYMSooKNDq1asvdqsAgL8DFx1kH3/8sWbMmKGnn376c/s2btyot99+W/
n5+Z9aq6ys1IEDB1RbW6vNmzeroaFBixYt8tbj8bhmz56tSZMmqbm5WWvWrNEjjzyi559//
mK3CwAY6ewSSLKNGzd+6vqf//xnmzhxou3fv98mTZpkjz/
+uLd28OBBk2Q7d+70rm3ZssV8Pp8dO3bMzMyeeeYZy83NtZ6eHq9nxYoVNmXKlAHvLRaLmSSKoijK4YrFYh
f8fp/
y35ElEgnNmzdPy5cv13XXXfep9cbGRuXk5KikpMS7VlZWprS0NDU1NXk9t912mzIyMrye8vJytba26qOPPu
r3vj09PYrH40kFABj5Uh5kP//5z5Wenq7777+/3/
VoNKq8vLyka+np6Ro7dqyi0ajXEwqFknrOfny253zV1dUKBoNeFRQUXOooAAAHpDTImpub9eSTT+rFF1+Uz
+dL5VNfUFVVlWKxmFdtbW2X9f4AgKGR0iB766231NHRocLCQqWnpys9PV1HjhzRgw8+qGuuuUaSFA6H1dHR
kfS4vr4+dXZ2KhwOez3t7e1JPWc/PttzPr/
fr0AgkFQAgJEvpUE2b9487du3T3v27PEqPz9fy5cv15tvvilJikQi6urqUnNzs/
e4+vp6JRIJlZaWej0NDQ3q7e31emprazVlyhTl5uamcssAANcN+Bjg/
+nu7raWlhZraWkxSfbYY49ZS0uLHTlypN/
+808tmpnNmTPHiouLrampybZv326TJ0+2iooKb72rq8tCoZDNmzfP9u/
fb+vXr7esrCx77rnnBrxPTi1SFEW5XwM5tXjRQbZ169Z+bzZ//vx++/
sLsuPHj1tFRYVlZ2dbIBCwBQsWWHd3d1LP3r17bebMmeb3+23ixIlWU1NzUfskyCiKotyvgQSZz8xMI1A8H
lcwGBzqbQAALkEsFrvgmQfeaxEA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0
ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4LQRG2Qj9O+FAsDflYF8Lx+xQXb8+PGh3gIA4BJ
1d3dfsCf9MuxjSIwdO1aSdPToUQWDwSHezd8mHo+roKBAbW1tF/
xT38PZSJiDGYaHkTCDNDLmGOwZzEzd3d3Kz8+/YO+IDbK0tL++2AwGg85+opwVCAScn0EaGXMww/
AwEmaQRsYcgznDQF+EjNgfLQIA/j4QZAAAp43YIPP7/
frxj38sv98/1Fv5m42EGaSRMQczDA8jYQZpZMwxnGbwGefUAQAOG7GvyAAAfx8IMgCA0wgyAIDTCDIAgNMI
MgCA00ZkkD399NO65pprNGbMGJWWlmrHjh1DvSVPdXW1brzxRl155ZXKy8vT17/+dbW2tib1nDp1SkuWLNG
4ceOUnZ2te+65R+3t7Uk9R48e1dy5c5WVlaW8vDwtX75cfX19l3MUT01NjXw+n5YtW+Zdc2WGY8eO6Tvf+Y
7GjRunzMxMTZ8+Xbt27fLWzUyrVq3ShAkTlJmZqbKyMh06dCjpOTo7O1VZWalAIKCcnBwtXLhQJ06cuCz7P
3PmjFauXKmioiJlZmbqi1/8on76058mvdHqcJuhoaFBd9xxh/Lz8+Xz+bRp06ak9VTtd9+
+fbr11ls1ZswYFRQUaPXq1Zdtjt7eXq1YsULTp0/XFVdcofz8fH33u9/VBx98MKzmuNC/
xbkWL14sn8+nJ554YljNIEmyEWb9+vWWkZFh//Vf/
2UHDhyw73//+5aTk2Pt7e1DvTUzMysvL7cXXnjB9u/fb3v27LF//Md/
tMLCQjtx4oTXs3jxYisoKLC6ujrbtWuX/cM//IPdfPPN3npfX59NmzbNysrKrKWlxV5//
XUbP368VVVVXfZ5duzYYddcc4195StfsaVLlzo1Q2dnp02aNMn++Z//2Zqamuz999+3N9980/77v//
b66mpqbFgMGibNm2yvXv32p133mlFRUV28uRJr2fOnDk2Y8YMe/
vtt+2tt96yL33pS1ZRUXFZZnj00Udt3LhxtnnzZjt8+LBt2LDBsrOz7cknnxy2M7z+
+uv28MMP2yuvvGKSbOPGjUnrqdhvLBazUChklZWVtn//fnv55ZctMzPTnnvuucsyR1dXl5WVldmvf/1r+
+Mf/2iNjY1200032Q033JD0HEM9x4X+Lc565ZVXbMaMGZafn2+PP/
74sJrBzGzEBdlNN91kS5Ys8T4+c+aM5efnW3V19RDu6rN1dHSYJNu2bZuZ/
fULYPTo0bZhwwav59133zVJ1tjYaGZ//
eRLS0uzaDTq9axdu9YCgYD19PRctr13d3fb5MmTrba21r72ta95QebKDCtWrLCZM2d+5noikbBwOGxr1qzx
rnV1dZnf77eXX37ZzMwOHjxokmznzp1ez5YtW8zn89mxY8cGb/P/Z+7cufa9730v6drdd99tlZWVTsxw/
jfPVO33mWeesdzc3KTPpRUrVtiUKVMuyxz92bFjh0myI0eOmNnwm+OzZvjzn/
9sEydOtP3799ukSZOSgmy4zDCifrR4+vRpNTc3q6yszLuWlpamsrIyNTY2DuHOPlssFpP0/+/
W39zcrN7e3qQZpk6dqsLCQm+GxsZGTZ8+XaFQyOspLy9XPB7XgQMHLtvelyxZorlz5ybtVXJnht/
+9rcqKSnRN7/5TeXl5am4uFi/
+MUvvPXDhw8rGo0mzREMBlVaWpo0R05OjkpKSryesrIypaWlqampadBnuPnmm1VXV6f33ntPkrR3715t375
dt99+uzMznCtV+21sbNRtt92mjIwMr6e8vFytra366KOPLtM0yWKxmHw+n3Jycrw9Dvc5EomE5s2bp+XLl+
u666771PpwmWFEBdlf/
vIXnTlzJumboySFQiFFo9Eh2tVnSyQSWrZsmW655RZNmzZNkhSNRpWRkeF9sp917gzRaLTfGc+uXQ7r16/
X7t27VV1d/ak1V2Z4//33tXbtWk2ePFlvvvmm7r33Xt1///1at25d0j4+7/
MpGo0qLy8vaT09PV1jx469LHM89NBD+va3v62pU6dq9OjRKi4u1rJly1RZWenMDOdK1X6Hw+fXuU6dOqUVK
1aooqLCe6d4F+b4+c9/rvT0dN1///39rg+XGUbsn3FxwZIlS7R//
35t3759qLdyUdra2rR06VLV1tZqzJgxQ72dv1kikVBJSYl+9rOfSZKKi4u1f/9+Pfvss5o/f/
4Q725gfvOb3+ill17Sr371K1133XXas2ePli1bpvz8fGdmGOl6e3v1rW99S2amtWvXDvV2Bqy5uVlPPvmkd
u/eLZ/
PN9Tb+Vwj6hXZ+PHjNWrUqE+djmtvb1c4HB6iXfXvvvvu0+bNm7V161ZdffXV3vVwOKzTp0+rq6srqf/
cGcLhcL8znl0bbM3Nzero6ND111+v9PR0paena9u2bXrqqaeUnp6uUCg07GeQpAkTJujaa69NuvblL39ZR4
8eTdrH530+hcNhdXR0JK339fWps7PzssyxfPly71XZ9OnTNW/ePD3wwAPeK2UXZjhXqvY7HD6/
pP8PsSNHjqi2tjbp73YN9zneeustdXR0qLCw0Ps6P3LkiB588EFdc801w2qGERVkGRkZuuGGG1RXV+ddSyQ
SqqurUyQSGcKd/
T8z03333aeNGzeqvr5eRUVFSes33HCDRo8enTRDa2urjh496s0QiUT0zjvvJH0Cnf0iOf8b82CYNWuW3nnn
He3Zs8erkpISVVZWev893GeQpFtuueVT/+vDe+
+9p0mTJkmSioqKFA6Hk+aIx+NqampKmqOrq0vNzc1eT319vRKJhEpLSwd9hk8+
+cT7I7JnjRo1SolEwpkZzpWq/
UYiETU0NKi3t9frqa2t1ZQpU5Sbm3tZZjkbYocOHdLvfvc7jRs3Lml9uM8xb9487du3L+nrPD8/
X8uXL9ebb745vGZI2bGRYWL9+vXm9/vtxRdftIMHD9qiRYssJycn6XTcULr33nstGAza73//e/
vwww+9+uSTT7yexYsXW2FhodXX19uuXbssEolYJBLx1s8eXZ89e7bt2bPH3njjDbvqqquG5Pj9WeeeWjRzY
4YdO3ZYenq6Pfroo3bo0CF76aWXLCsry375y196PTU1NZaTk2Ovvvqq7du3z+66665+j4IXFxdbU1OTbd+
+3SZPnnzZjt/Pnz/fJk6c6B2/f+WVV2z8+PH2ox/
9aNjO0N3dbS0tLdbS0mKS7LHHHrOWlhbvNF8q9tvV1WWhUMjmzZtn+/fvt/Xr11tWVlZKj3x/3hynT5+2O+
+8066++mrbs2dP0tf6uaf3hnqOC/1bnO/8U4vDYQazEXj83szsP/
7jP6ywsNAyMjLspptusrfffnuot+SR1G+98MILXs/JkyftBz/4geXm5lpWVpZ94xvfsA8//DDpef70pz/
Z7bffbpmZmTZ+/Hh78MEHrbe39zJP8//
ODzJXZnjttdds2rRp5vf7berUqfb8888nrScSCVu5cqWFQiHz+/
02a9Ysa21tTeo5fvy4VVRUWHZ2tgUCAVuwYIF1d3dflv3H43FbunSpFRYW2pgxY+wLX/
iCPfzww0nfLIfbDFu3bu33a2D+/Pkp3e/
evXtt5syZ5vf7beLEiVZTU3PZ5jh8+PBnfq1v3bp12MxxoX+L8/
UXZEM9g5kZf48MAOC0EfU7MgDA3x+CDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0ggwA4DSCDADgNIIMAOA0g
gwA4DSCDADgtP8FwPeruHk+YigAAAAASUVORK5CYII="},"metadata":{}}]},
{"cell_type":"code","source":"modelo = torch.hub.load('pytorch/vision:v0.10.0',
'vgg11', pretrained=True)","metadata":{"id":"vvKON_-4z95V","colab":
{"base_uri":"https://localhost:8080/"},"executionInfo":
{"status":"ok","timestamp":1728251816833,"user_tz":300,"elapsed":9866,"user":
{"displayName":"DAVID SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"}},"outputId":"518d2b12-2ff8-4919-c1c9-
887d08768f53","execution":{"iopub.status.busy":"2024-10-
07T18:36:32.812687Z","iopub.execute_input":"2024-10-
07T18:36:32.813029Z","iopub.status.idle":"2024-10-
07T18:36:34.433425Z","shell.execute_reply.started":"2024-10-
07T18:36:32.812993Z","shell.execute_reply":"2024-10-
07T18:36:34.432273Z"},"trusted":true},"execution_count":11,"outputs":
[{"name":"stderr","text":"Using cache found in
/root/.cache/torch/hub/pytorch_vision_v0.10.0\n","output_type":"stream"}]},
{"cell_type":"code","source":"#from torchsummary import summary\
n#modelresnet=resnet101(pretrained=True)\n#print(modelresnet.layer4)\
n#","metadata":{"id":"1oROOdM80KW9","colab":{"base_uri":"https://
localhost:8080/"},"executionInfo":
{"status":"ok","timestamp":1728251820038,"user_tz":300,"elapsed":3213,"user":
{"displayName":"DAVID SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"}},"outputId":"8a6a8415-9e54-4597-de94-
2005ab2761b1","execution":{"iopub.status.busy":"2024-10-
07T18:36:34.436012Z","iopub.execute_input":"2024-10-
07T18:36:34.436418Z","iopub.status.idle":"2024-10-
07T18:36:34.441784Z","shell.execute_reply.started":"2024-10-
07T18:36:34.436378Z","shell.execute_reply":"2024-10-
07T18:36:34.440681Z"},"trusted":true},"execution_count":12,"outputs":[]},
{"cell_type":"code","source":"device = torch.device(\"cuda\" if
torch.cuda.is_available() else \"cpu\")\nprint(f\"Using device: {device}\")\
ntorch.set_default_device(device)","metadata":{"id":"In5aLgpMfgr5","colab":
{"base_uri":"https://localhost:8080/"},"executionInfo":
{"status":"ok","timestamp":1728255917927,"user_tz":300,"elapsed":10,"user":
{"displayName":"DAVID
SANTIAGO SANCHEZ CEPEDA","userId":"09385389865282990454"}},"outputId":"6dd1e892-
d2ce-4958-f9aa-0a93d81b6ea6","execution":{"iopub.status.busy":"2024-10-
07T18:36:34.443168Z","iopub.execute_input":"2024-10-
07T18:36:34.443571Z","iopub.status.idle":"2024-10-
07T18:36:34.508903Z","shell.execute_reply.started":"2024-10-
07T18:36:34.443536Z","shell.execute_reply":"2024-10-
07T18:36:34.507587Z"},"trusted":true},"execution_count":13,"outputs":
[{"name":"stdout","text":"Using device: cuda\n","output_type":"stream"}]},
{"cell_type":"code","source":"\nclass game():\n def __init__(self):\n
self.x=450\n\n def reset(self):\n self.x=450\n self.y=0\n self.canvas =
np.zeros((1500, 1500,3))\n self.canvas[self.y:self.y+250,self.x:self.x+250]=img\
n print(self.canvas.shape)\n #resize image\n
self.canvas=preprocess(self.canvas)\n return self.canvas,0,False,{}\n def
step(self,action):\n self.canvas=np.zeros((1500,1500,3))\n print(self.y)\n
freefall=self.y+(1/2)*9.8*(2)**2\n print(\"yfuture\")\n print(freefall)\n\n
self.y=freefall\n if self.y>1500-250:\n done=True\n return
preprocess(self.canvas),1,done,{}\n else:\n done=False\n
self.y=int(freefall)\n print()\n
self.canvas[self.y:self.y+250,self.x:self.x+250]=img\n #resize image\n
stateaf=preprocess(self.canvas)\n reward=self.reward(action)\n info={}\n
return stateaf,reward,done,info\n\n\n def reward(self,action):\n
#print((self.y,action))\n return
100/(1+torch.nn.functional.mse_loss(torch.tensor(action),torch.tensor(self.y)))","m
etadata":{"id":"q6PTQIccn5bB","execution":{"iopub.status.busy":"2024-10-
07T18:36:34.510541Z","iopub.execute_input":"2024-10-
07T18:36:34.511222Z","iopub.status.idle":"2024-10-
07T18:36:34.524182Z","shell.execute_reply.started":"2024-10-
07T18:36:34.511182Z","shell.execute_reply":"2024-10-
07T18:36:34.522957Z"},"trusted":true},"execution_count":14,"outputs":[]},
{"cell_type":"code","source":"class ResBlock(torch.nn.Module):\n def
__init__(self,inn,outt,downsample):\n super(ResBlock,self).__init__()\n
self.conv1=torch.nn.Conv2d(inn,outt,3,padding=1)\n
self.batchnorm1=torch.nn.BatchNorm2d(outt)\n self.relu=torch.nn.ReLU()\n\n
self.downsample = downsample\n self.avgpool=torch.nn.AvgPool2d(2,2)\n if
self.downsample or inn != outt:\n self.identity_downsample =
nn.Conv2d(inn, outt, kernel_size=1, stride=1)\n self.identity_batchnorm
= nn.BatchNorm2d(outt)\n else:\n self.identity_downsample = None\n
def forward(self,x):\n residual=self.conv1(x)\n
residual=self.batchnorm1(residual)\n residual=self.relu(residual)\n identity
= x\n #print(\"identity shape\")\n #print(identity.shape)\n
#print(\"residual shape\")\n #print(residual.shape)\n if
self.identity_downsample is not None:\n identity =
self.identity_downsample(identity)\n #print(\"identity shape2\")\n
#print(identity.shape)\n identity = self.identity_batchnorm(identity)\n\n
# Add residual and identity\n output = residual + identity\n output =
self.relu(output)\n output = self.avgpool(output)\n return output\n
else:\n output = residual + identity\n output = self.relu(output)\n
output = self.avgpool(output)\n return output\n\n return output\n\n\
n","metadata":{"id":"HfF9Q9-6FTOP","execution":{"iopub.status.busy":"2024-10-
07T18:36:34.525941Z","iopub.execute_input":"2024-10-
07T18:36:34.526401Z","iopub.status.idle":"2024-10-
07T18:36:34.539323Z","shell.execute_reply.started":"2024-10-
07T18:36:34.526323Z","shell.execute_reply":"2024-10-
07T18:36:34.538234Z"},"trusted":true},"execution_count":15,"outputs":[]},
{"cell_type":"code","source":"class actorr(torch.nn.Module):\n def
__init__(self,limit):\n super(actorr,self).__init__()\n
self.resBlock1=ResBlock(3,32,True)\n self.resBlock2=ResBlock(32,32,True)\n
self.resBlock3=ResBlock(32,64,True)\n self.resBlock4=ResBlock(64,64,True)\n
#self.resnet=resnet18(pretrained=False)\n
#self.vgg=torch.hub.load('pytorch/vision:v0.10.0', 'vgg11', pretrained=True)\n\n
#self.vgg=torch.nn.Sequential(*list(self.vgg.children())[:-1])\n
self.flatten=torch.nn.Flatten()\n self.fcmean=torch.nn.Linear(100,1)\n
self.fcvar=torch.nn.Linear(12544,200)\n
self.fcvar2=torch.nn.Linear(200,100)\n self.fcvar3=torch.nn.Linear(100,1)\n
#self.instancenorm3=torch.nn.RMSNorm((1,200),elementwise_affine=True)\n
#self.instancenorm2=torch.nn.RMSNorm((1,100),elementwise_affine=True)\n
#self.instancenorm1=torch.nn.RMSNorm((1,200),elementwise_affine=True)\n
#self.groupnorm1=torch.nn.GroupNorm(num_groups=32,num_channels=512)\n
self.selu1=torch.nn.SELU()\n self.selu2=torch.nn.SELU()\n
self.selu3=torch.nn.SELU()\n self.sigmoid=torch.nn.Sigmoid()\n
self.limit=limit\n #initialize fc\n
#torch.nn.init.xavier_uniform_(self.fcmean.weight)\n
#torch.nn.init.xavier_uniform_(self.fcvar.weight)\n
#torch.nn.init.xavier_uniform_(self.fcvar2.weight)\n
#torch.nn.init.xavier_uniform_(self.fcvar3.weight)\n #remove last fc layer
withou\n #self.resnet.fc=torch.nn.Identity()\n
#self.vgg.classifier=torch.nn.Identity()\n\n\n #for param in
self.resnet.parameters():\n #param.requires_grad = False\n
#unfreeze with a probability\n #for param in self.resnet.parameters():\n
#delta=random.random()\n #if delta<self.limit:\n
#param.requires_grad = True\n #self.resnet.layer4.requires_grad_(True)\n
#self.resnet.layer3.requires_grad_(True)\n
#self.resnet.layer2.requires_grad_(True)\n
#self.resnet.layer1.requires_grad_(True)\n #for param in
self.vgg.parameters():\n #param.requires_grad = False\n for name,
param in self.named_parameters():\n print(f\"Parameter: {name} |
requires_grad: {param.requires_grad}\")\n\n\n\n def forward(self,x):\n
x=self.resBlock1(x)\n x=self.resBlock2(x)\n x=self.resBlock3(x)\n
x=self.resBlock4(x)\n #x=self.vgg(x)\n #x=self.groupnorm1(x)\n
#print(\"ex sheip\")\n #print(x.shape)\n x=self.flatten(x)\n\n\n
x=self.fcvar(x)\n #x=self.instancenorm1(x)\n #print(\"shapefif\")\n
#print(x.shape)\n #dinamic instance\n #x=torch.reshape(x,(-1,1,200))\
n #tensorrr=torch.Tensor([])\n #for i in x:\n
#print(i.shape)\n\n\n #i=self.instancenorm1(i)\n #concat\n
#tensorrr=torch.cat((tensorrr,i),0)\n #x=tensorrr\n\n
#x=torch.reshape(x,(-1,200))\n #x=self.selu1(x)\n x=torch.nn.SELU()
(x)\n\n #x=torch.nn.Dropout(0.5)(x)\n\n #x=tensorr\n
x=self.fcvar2(x)\n #x=torch.nn.InstanceNorm1d(x.shape[0])(x)\n
#x=self.selu2(x)\n x=torch.nn.SELU()(x)\n\n #x=torch.nn.Dropout(0.5)
(x)\n #x=self.instancenorm2(x)\n #x=self.selu2(x)\n
variance=self.fcvar3(x)\n mean=self.fcmean(x)\n
x=torch.cat((mean,variance),1)\n\n #concat the mean and variance\n
#x=self.instancenorm3(x)\n #x=self.sigmoid(x)\n\n\n\n
x=torch.nn.Sigmoid()(x)\n #x=torch.nn.ReLU6()(x)\n\n\n\n\n\n return
x\n def act(self,x,eps,deterministic):\n #print(\"input sheip\")\n
#print(x.shape)\n\n x=self.forward(x)\n #print(\"mean and std\")\n\n\
n #static variance\n variance=x[:,1]+1e-5\n
#variance=torch.ones(x.shape[0])\n variance=torch.clamp(variance,min=1e-
3,max=1.0*eps)\n variance=torch.reshape(variance,(-1,1))\n\n
#print(x[:,0])\n #print(x[:,1])\n #clampvar\n\n
cov=torch.diag(variance)\n dist=torch.distributions.Normal(x[:,0],variance)\
n if deterministic:\n action=x[:,0]*1500\n return
action,0,0,action\n action=dist.rsample()\n
action=torch.reshape(action,(-1,1))\n #print(\"action\")\n
#print(action)\n\n\n log_prob=dist.log_prob(action)\n
log_prob=log_prob\n actionunscaled=action\n action=action*1500\n
#print(\"log prob\")\n #print(log_prob)\n entropy=dist.entropy()\n
entropy=torch.mean(entropy)\n #print(\"entropy\")\n #print(entropy)\n
log_prob=torch.reshape(log_prob,(-1,1))\n if deterministic:\n
print(\"deterministaaaa\")\n action=x[:,0]*1500\n
print(\"action determinista\")\n print(action)\n\n\n return
action,log_prob,entropy,actionunscaled\n def
actonlogprob(self,x,eps,deterministic,actions):\n meaandavg=torch.Tensor([])\n
#print(\"input sheip\")\n #print(x.shape)\n for i in x:\n
i=torch.unsqueeze(i,0)\n\n i=self.forward(i)\n #print(\"actionss\")\n
#print(actions)\n meaandavg=torch.cat((meaandavg,i),0)\n x=meaandavg\n
#static variance\n variance=x[:,1]+1e-5\n #x=self.forward(x)\n
#variance=torch.ones(x.shape[0])\n variance=torch.clamp(variance,min=1e-
3,max=1.0*eps)\n dist=torch.distributions.Normal(x[:,0],variance)\n
logprobs=dist.log_prob(actions)\n logprobs=logprobs\n
entropy=dist.entropy()\n entropy=torch.mean(entropy)\n
#print(\"logprobs\")\n #print(logprobs)\n #print(\"entropy\")\n
#print(entropy)\n #print(\"mean and std\")\n #print(x[:,0])\n
#print(x[:,1])\n graph=plt.plot(x[:,0].cpu().detach())\n #save\n
#remove graph\n plt.savefig('graphmean.png')\n plt.clf()\n
#plt.show()\n graph=plt.plot(x[:,1].cpu().detach())\n #save\n
plt.savefig('graphstd.png')\n
plt.clf()\n #plt.show()\n\n\n\n return logprobs,entropy\n\nclass
qfunction(torch.nn.Module):\n def __init__(self):\n
super(qfunction,self).__init__()\n self.resnet=resnet18(pretrained=True)\n
self.vgg=torch.hub.load('pytorch/vision:v0.10.0', 'vgg11', pretrained=True)\n
self.vgg=torch.nn.Sequential(*list(self.vgg.children())[:-1])\n
self.resnet=torch.nn.Sequential(*list(self.resnet.children())[:-1])\n
self.flatten=torch.nn.Flatten()\n self.fc=torch.nn.Linear(512,100)\n
self.fc1=torch.nn.Linear(100,10)\n self.fc2=torch.nn.Linear(10,1)\n\n\n
self.conv1daction=torch.nn.Linear(1,32)\n
self.batchnorm=torch.nn.InstanceNorm1d(32)\n self.selu=torch.nn.SELU()\n
self.conv2daction=torch.nn.Linear(32,32)\n
self.batchnorm2=torch.nn.InstanceNorm1d(32)\n
self.convidentityaction=torch.nn.Linear(1,32)\n #initialize fc\n
torch.nn.init.xavier_uniform_(self.fc.weight)\n def forward(self,x):\n
x=self.resnet(x)\n #x=self.vgg(x)\n x=self.flatten(x)\n
x=self.fc(x)\n x=torch.nn.SELU()(x)\n x=self.fc1(x)\n
x=torch.nn.SELU()(x)\n x=self.fc2(x)\n return x","metadata":
{"id":"dcPiRY5ZnM6F","execution":{"iopub.status.busy":"2024-10-
07T18:36:34.540823Z","iopub.execute_input":"2024-10-
07T18:36:34.541299Z","iopub.status.idle":"2024-10-
07T18:36:34.578077Z","shell.execute_reply.started":"2024-10-
07T18:36:34.541259Z","shell.execute_reply":"2024-10-
07T18:36:34.576982Z"},"trusted":true},"execution_count":16,"outputs":[]},
{"cell_type":"markdown","source":"","metadata":{"id":"Rgksfug-Ntfx"}},
{"cell_type":"code","source":"from collections import deque","metadata":{"id":"-
wDlx0E6ySAf","execution":{"iopub.status.busy":"2024-10-
07T18:36:34.581090Z","iopub.execute_input":"2024-10-
07T18:36:34.581542Z","iopub.status.idle":"2024-10-
07T18:36:34.592623Z","shell.execute_reply.started":"2024-10-
07T18:36:34.581498Z","shell.execute_reply":"2024-10-
07T18:36:34.591314Z"},"trusted":true},"execution_count":17,"outputs":[]},
{"cell_type":"markdown","source":"","metadata":{}},
{"cell_type":"code","source":"class train():\n def
__init__(self,env,t,gamma,actor,critic,epochs,initial_eps,decay,deterministic,lambd
ad,epsilon,limit):\n self.epsilon=epsilon\n self.env=env\n self.t=t\n
self.gamma=gamma\n self.policy_net=actor(limit)\n self.critic_net=critic()\n
self.optimizeractor=torch.optim.Adam(self.policy_net.parameters(),lr=0.00006,weight
_decay=0.4)\n
self.optimizercritic=torch.optim.Adam(self.critic_net.parameters(),lr=0.004,weight_
decay=0.2)\n #clip grad\n
#torch.nn.utils.clip_grad_value_(self.policy_net.parameters(), clip_value=1.0)\n
#torch.nn.utils.clip_grad_value_(self.critic_net.parameters(), clip_value=1.0)\n
self.epochs=epochs\n self.acc_rewards=[]\n
#self.policy_net.resnet.requires_grad_(False)\n
self.critic_net.resnet.requires_grad_(False)\n
#self.policy_net.vgg.requires_grad_(False)\n
self.critic_net.vgg.requires_grad_(False)\n\n self.eps=initial_eps\n
self.decay=decay\n self.avgs=[]\n self.deterministic=deterministic\n
self.lmbda=lambdad\n\n def millonariosonacional(self,states):\n
al=random.random()\n if al<self.eps:\n print(\"millonarios\")\n
#create batch of random variables\n meaandesv = torch.rand((states.shape[0],
2))\n mean = meaandesv[:, 0]\n stddev = torch.clamp(meaandesv[:, 1],
min=1e-3, max=1.0)\n cov_matrix = torch.diag(stddev**2)\n
dist=torch.distributions.MultivariateNormal(mean,cov_matrix)\n
action=dist.rsample()\n log_prob=dist.log_prob(action)\n\n
action=action*1500\n\n print(action,log_prob)\n return action,log_prob\n\
n else:\n print(\"nacional\")\n
action,lobg_prob=self.policy_net.act(states)\n return action,lobg_prob\n\n\n
def runtimesteps(self,t):\n ts=t\n initial_arr=deque(maxlen=ts+100)\n
rewards=deque(maxlen=ts+100)\n dones=deque(maxlen=ts+100)\n
rotwarr=deque(maxlen=ts+100)\n actions=deque(maxlen=ts+100)\n
log_probs=deque(maxlen=ts+100)\n advantages=torch.Tensor([])\n
gaereturnss=torch.Tensor([])\n\n\n\n while t>=0:\n
rotwsub=deque(maxlen=ts+100)\n initial_intern=deque(maxlen=ts+100)\n
dones_intern=deque(maxlen=ts+100)\n
initial_state,reward,done,info=self.env.reset()\n acc_reward=0\n
trayectories=0\n\n\n while not done:\n #print(\"la forma\")\n
#print(initial_state.shape)\n
action,log_prob,_,actionunscaled=self.policy_net.act(initial_state.unsqueeze(0).to(
\"cuda\"),self.eps,self.deterministic)\n action=action\n
actions.append(actionunscaled)\n log_prob=log_prob\n
#action=torch.sigmoid(action)\n #action=action*1500\n
state,reward,done,info=self.env.step(action)\n
initial_intern.append(initial_state.detach())\n\n\n #print(reward)\n
rewards.append(reward)\n dones_intern.append(done)\n
log_probs.append(log_prob.detach())\n rotwsub.append(reward)\n t-=1\n
initial_state=state\n acc_reward+=reward\n
#advantages=advantages+self.gae(initial_intern,rotwsub,dones_intern)\n
gaeadvantages,gaereturns=self.gae(initial_intern,rotwsub,dones_intern)\n
advantages=torch.cat((advantages,gaeadvantages),0)\n
gaereturnss=torch.cat((gaereturnss,gaereturns),0)\n dones=dones+dones_intern\n
initial_arr=initial_arr+initial_intern\n self.acc_rewards.append(acc_reward)\n
trayectories+=1\n\n if len(self.acc_rewards)>=5:\n\n
batchacc=self.acc_rewards[-5:]\n avg=sum(batchacc)/len(batchacc)\n
self.avgs.append(avg)\n print(avg)\n #plt.plot(self.avgs)\n
#plt.show()\n\n rotwarr+=self.rewontheway(rotwsub)\n return
initial_arr,rewards,actions,dones,rotwarr,log_probs,advantages,gaereturnss,trayecto
ries\n def rewontheway(self,rotwsub):\n rotw=torch.Tensor([0])\n
output=deque(maxlen=len(rotwsub))\n print(rotwsub)\n rotwsub.reverse()\n
print(rotwsub)\n for z,i in enumerate(rotwsub):\n
rotw=i+rotw.clone()*self.gamma**(len(rotwsub)-z)\n\n output.insert(0,rotw)\n
return output\n def train(self):\n
initial_states,rewards,actions,dones,rotwar,log_pro,advantages,gaereturnss,trayecto
ries=self.runtimesteps(self.t)\n
tensorin=torch.stack(tuple(initial_states)).to(\"cuda\")\n
rotwarr=torch.stack(tuple(rotwar)).to(\"cuda\")\n
log_probs=torch.Tensor(log_pro).to(\"cuda\")\n #print(\"log_probs1\")\n
#print(log_probs)\n log_probs=torch.reshape(log_probs,(-1,1))\n
#print(\"log_probs2\")\n #print(log_probs)\n
actions=torch.Tensor(actions).to(\"cuda\")\n tensorin=tensorin\n\n\n\n for i
in range(self.epochs):\n clear_output()\n\n #1\n
criticeval=self.critic_net(tensorin)\n advantagee=advantages\n #2\n
#advantagee=((advantage-advantage.mean())/(advantage.std()+1e-5))\n\n\n
logprob,entropy=self.policy_net.actonlogprob(tensorin,self.eps,self.deterministic,a
ctions)\n logprob=torch.reshape(logprob,(-1,1))\n #print(\"logprob\")\n
#print(logprob)\n #print(\"log_probs\")\n #print(log_probs)\n
#action=torch.sigmoid(action)\n #action=action*1500\n
ratio=torch.exp(logprob-log_probs)\n #print(\"ratio\")\n
#print(ratio.shape)\n #ratio=torch.clamp(ratio,1-self.epsilon,1+self.epsilon)\
n #print(\"ratio\")\n #print(ratio)\n #print(\"advantagee\")\n
#print(advantagee)\n surr1=ratio*advantagee\n surr2=(torch.clamp(ratio,1-
self.epsilon,1+self.epsilon)*advantagee)\n loss1=(-
torch.min(surr1,surr2).sum())/len(initial_states)\n #print(\"loss1\")\n
#print(loss1)\n #print(\"lossss 1\")\n #print(loss1)\n #print
gradients\n\n loss2=F.mse_loss(criticeval,gaereturnss)\n
#print(\"loss2\")\n #print(loss2)\n #print(\"entrphyss\")\n
#print(entropy)\n\n\n\n finalloss=1*loss1+0.5*loss2-0.1*entropy\n
#print(\"finalloss\")\n #print(finalloss)\n
self.optimizeractor.zero_grad()\n self.optimizercritic.zero_grad()\n
finalloss.backward(retain_graph=True)\n #clip grad norm\n
torch.nn.utils.clip_grad_norm_(self.policy_net.parameters(), max_norm=1.0)\n
torch.nn.utils.clip_grad_norm_(self.critic_net.parameters(), max_norm=10.0)\n
self.optimizeractor.step()\n self.optimizercritic.step()\n print(\"Actor
Gradients:\")\n for name, param in self.policy_net.named_parameters():\n
if param.grad is not None:\n print(f\"Parameter: {name} | Grad Norm:
{param.grad.norm()}\")\n print(\"Critic Gradients:\")\n for name, param
in self.critic_net.named_parameters():\n if param.grad is not None:\n
print(f\"Parameter: {name} | Grad Norm: {param.grad.norm()}\")\n
self.eps=self.eps*self.decay\n print(\"epsilon\")\n print(self.eps)\n if
self.eps<0.01:\n self.eps=0.01\n\n
print({\"loss1\":loss1,\"loss2\":loss2,\"actions\":actions})\n def
gae(self,states,rewards,done):\n returns = deque(maxlen=300)\n gae = 0\n
print(\"zs\")\n states=torch.stack(tuple(states))\n print(rewards)\n
print(done)\n values=self.critic_net(states.to(\"cuda\")).detach()\n\n
#concat 0 tensor\n values=torch.cat((values,torch.Tensor([[0]])),0)\n
print(values.shape)\n for i in reversed(range(len(rewards))):\n delta =
rewards[i] + self.gamma * values[i + 1,0] - values[i,0]\n gae = delta +
self.gamma * self.lmbda * gae\n returns.insert(0, gae.detach() +
values[i].detach())\n\n adv = returns\n adv = torch.stack(tuple(adv))\n
#print(\"adv\")\n #print(adv)\n gaereturns=adv-values[:-1]\n
#print(\"gaereturns\")\n #print(gaereturns)\n
return ((adv - adv.mean()) / (adv.std() + 1e-10)),gaereturns\n\n\n","metadata":
{"id":"0aenyK7Nfn_0","execution":{"iopub.status.busy":"2024-10-
07T18:36:34.595033Z","iopub.execute_input":"2024-10-
07T18:36:34.595475Z","iopub.status.idle":"2024-10-
07T18:36:34.639468Z","shell.execute_reply.started":"2024-10-
07T18:36:34.595423Z","shell.execute_reply":"2024-10-
07T18:36:34.638354Z"},"trusted":true},"execution_count":18,"outputs":[]},
{"cell_type":"code","source":"","metadata":
{"id":"0dSCB7hMUUZo"},"execution_count":null,"outputs":[]},
{"cell_type":"code","source":"","metadata":
{"id":"UGYCDSpojUUY"},"execution_count":null,"outputs":[]},
{"cell_type":"code","source":"","metadata":
{"id":"cprNzShn5W_n"},"execution_count":null,"outputs":[]},
{"cell_type":"code","source":"","metadata":{"id":"1ZiAo4h78ZfA","colab":
{"base_uri":"https://localhost:8080/","height":141},"executionInfo":
{"status":"error","timestamp":1728246724522,"user_tz":300,"elapsed":389,"user":
{"displayName":"DAVID SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"}},"outputId":"b918d089-35b4-45bf-986f-
26b73d285b6f","trusted":true},"execution_count":null,"outputs":[]},
{"cell_type":"code","source":"\n\
ntorch.set_default_tensor_type('torch.cuda.FloatTensor')\n\nfrom IPython.display
import clear_output\n\n\n\n\n\n\ntorch.autograd.set_detect_anomaly(True)\n\
ntrains=train(game(),100,0.99,actorr,qfunction,5,1,0.999,False,0.95,0.5,0.1)\
npipeline=400\nfor i in range(pipeline):\n clear_output(wait=True)\n
trains.train()","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":
1000},"id":"UzDSDHvto1D-","outputId":"c1dc4155-da81-4ccd-aa66-
e082ff93a701","executionInfo":
{"status":"ok","timestamp":1728256378056,"user_tz":300,"elapsed":440455,"user":
{"displayName":"DAVID SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"}},"execution":{"iopub.status.busy":"2024-
10-07T18:36:34.640833Z","iopub.execute_input":"2024-10-
07T18:36:34.641223Z","iopub.status.idle":"2024-10-
07T19:48:30.109874Z","shell.execute_reply.started":"2024-10-
07T18:36:34.641185Z","shell.execute_reply":"2024-10-
07T19:48:30.108102Z"},"trusted":true},"execution_count":19,"outputs":[{"traceback":
["\
u001b[0;31m------------------------------------------------------------------------
---\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m
Traceback (most recent call last)","Cell \u001b[0;32mIn[19], line 16\u001b[0m\n\
u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \
u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(pipeline):\n\
u001b[1;32m 15\u001b[0m clear_output(wait\u001b[38;5;241m=\u001b[39m\
u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m---> 16\u001b[0m \
u001b[43mtrains\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\
u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n","Cell \u001b[0;32mIn[18],
line 150\u001b[0m, in \u001b[0;36mtrain.train\u001b[0;34m(self)\u001b[0m\n\
u001b[1;32m 145\u001b[0m advantagee\u001b[38;5;241m=\u001b[39madvantages\n\
u001b[1;32m 146\u001b[0m \u001b[38;5;66;03m#2\u001b[39;00m\n\u001b[1;32m 147\
u001b[0m
\u001b[38;5;66;03m#advantagee=((advantage-advantage.mean())/(advantage.std()+1e-
5))\u001b[39;00m\n\u001b[0;32m--> 150\u001b[0m logprob,entropy\u001b[38;5;241m=\
u001b[39m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\
u001b[43mpolicy_net\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\
u001b[43mactonlogprob\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtensorin\u001b[49m\
u001b[43m,\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\
u001b[39;49m\u001b[43meps\u001b[49m\u001b[43m,\u001b[49m\u001b[38;5;28;43mself\
u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdeterministic\u001b[49m\
u001b[43m,\u001b[49m\u001b[43mactions\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m
151\u001b[0m logprob\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\
u001b[39mreshape(logprob,(\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m,\
u001b[38;5;241m1\u001b[39m))\n\u001b[1;32m 152\u001b[0m \
u001b[38;5;66;03m#print(\"logprob\")\u001b[39;00m\n\u001b[1;32m 153\u001b[0m \
u001b[38;5;66;03m#print(logprob)\u001b[39;00m\n\u001b[1;32m 154\u001b[0m \
u001b[38;5;66;03m#print(\"log_probs\")\u001b[39;00m\n\u001b[1;32m 155\u001b[0m \
u001b[38;5;66;03m#print(log_probs)\u001b[39;00m\n\u001b[1;32m 156\u001b[0m \
u001b[38;5;66;03m#action=torch.sigmoid(action)\u001b[39;00m\n\u001b[1;32m 157\
u001b[0m \u001b[38;5;66;03m#action=action*1500\u001b[39;00m\n","Cell \
u001b[0;32mIn[16], line 170\u001b[0m, in \u001b[0;36mactorr.actonlogprob\
u001b[0;34m(self, x, eps, deterministic, actions)\u001b[0m\n\u001b[1;32m 167\
u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m
x:\n\u001b[1;32m 168\u001b[0m i\u001b[38;5;241m=\u001b[39mtorch\
u001b[38;5;241m.\u001b[39munsqueeze(i,\u001b[38;5;241m0\u001b[39m)\n\u001b[0;32m-->
170\u001b[0m i\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;43mself\u001b[39;49m\
u001b[38;5;241;43m.\u001b[39;49m\u001b[43mforward\u001b[49m\u001b[43m(\u001b[49m\
u001b[43mi\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 171\u001b[0m \
u001b[38;5;66;03m#print(\"actionss\")\u001b[39;00m\n\u001b[1;32m 172\
u001b[0m \u001b[38;5;66;03m#print(actions)\u001b[39;00m\n\u001b[1;32m 173\
u001b[0m meaandavg\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\
u001b[39mcat((meaandavg,i),\u001b[38;5;241m0\u001b[39m)\n","Cell \
u001b[0;32mIn[16], line 57\u001b[0m, in \u001b[0;36mactorr.forward\
u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 55\u001b[0m x\u001b[38;5;241m=\
u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mresBlock1(x)\n\
u001b[1;32m 56\u001b[0m x\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\
u001b[39m\u001b[38;5;241m.\u001b[39mresBlock2(x)\n\u001b[0;32m---> 57\u001b[0m x\
u001b[38;5;241m=\u001b[39m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\
u001b[39;49m\u001b[43mresBlock3\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\
u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 58\u001b[0m x\u001b[38;5;241m=\
u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mresBlock4(x)\n\
u001b[1;32m 59\u001b[0m \u001b[38;5;66;03m#x=self.vgg(x)\u001b[39;00m\n\
u001b[1;32m 60\u001b[0m \u001b[38;5;66;03m#x=self.groupnorm1(x)\u001b[39;00m\n\
u001b[1;32m 61\u001b[0m \u001b[38;5;66;03m#print(\"ex sheip\")\u001b[39;00m\n\
u001b[1;32m 62\u001b[0m \u001b[38;5;66;03m#print(x.shape)\u001b[39;00m\n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/
module.py:1553\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self,
*args, **kwargs)\u001b[0m\n\u001b[1;32m 1551\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\
u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \
u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m#
type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1552\u001b[0m \
u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1553\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\
u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\
u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\
u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\
u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\
n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/
module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args,
**kwargs)\u001b[0m\n\u001b[1;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't
have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m
1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\
u001b[39;00m\n\u001b[1;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \
u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\
u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\
u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\
u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks
\u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\
u001b[39m_forward_pre_hooks\n\u001b[1;32m 1560\u001b[0m \
u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\
u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1561\u001b[0m \
u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\
u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1562\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\
u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\
u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\
u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\
u001b[1;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m
1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\
u001b[39;00m\n","Cell \u001b[0;32mIn[15], line 32\u001b[0m, in \
u001b[0;36mResBlock.forward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 30\
u001b[0m \u001b[38;5;66;03m# Add residual and identity\u001b[39;00m\n\u001b[1;32m
31\u001b[0m output \u001b[38;5;241m=\u001b[39m residual \u001b[38;5;241m+\u001b[39m
identity\n\u001b[0;32m---> 32\u001b[0m output \u001b[38;5;241m=\u001b[39m \
u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrelu\
u001b[49m\u001b[43m(\u001b[49m\u001b[43moutput\u001b[49m\u001b[43m)\u001b[49m\n\
u001b[1;32m 33\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\
u001b[39m\u001b[38;5;241m.\u001b[39mavgpool(output)\n\u001b[1;32m 34\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m output\n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/
module.py:1553\u001b[0m,
in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\
u001b[0m\n\u001b[1;32m 1551\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \
u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\
u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\
u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m
1552\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1553\u001b[0m
\u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\
u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\
u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\
u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\
u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\
n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/
module.py:1562\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args,
**kwargs)\u001b[0m\n\u001b[1;32m 1557\u001b[0m \u001b[38;5;66;03m# If we don't
have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m
1558\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\
u001b[39;00m\n\u001b[1;32m 1559\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \
u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\
u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\
u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\
u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks
\u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\
u001b[39m_forward_pre_hooks\n\u001b[1;32m 1560\u001b[0m \
u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\
u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1561\u001b[0m \
u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\
u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1562\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\
u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\
u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\
u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\
u001b[1;32m 1564\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m
1565\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\
u001b[39;00m\n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/modules/
activation.py:104\u001b[0m, in \u001b[0;36mReLU.forward\u001b[0;34m(self, input)\
u001b[0m\n\u001b[1;32m 103\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \
u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \
u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\
u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 104\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\
u001b[39;49m\u001b[43mrelu\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\
u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minplace\u001b[49m\
u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\
u001b[38;5;241;43m.\u001b[39;49m\u001b[43minplace\u001b[49m\u001b[43m)\u001b[49m\
n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/functional.py:1496\
u001b[0m, in \u001b[0;36mrelu\u001b[0;34m(input, inplace)\u001b[0m\n\u001b[1;32m
1490\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124mr\u001b[39m\
u001b[38;5;124;03m\"\"\"relu(input, inplace=False) -> Tensor\u001b[39;00m\n\
u001b[1;32m 1491\u001b[0m \n\u001b[1;32m 1492\u001b[0m \
u001b[38;5;124;03mApplies the rectified linear unit function element-wise. See\
u001b[39;00m\n\u001b[1;32m 1493\u001b[0m \
u001b[38;5;124;03m:class:`~torch.nn.ReLU` for more details.\u001b[39;00m\n\
u001b[1;32m 1494\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m
1495\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m has_torch_function_unary(\
u001b[38;5;28minput\u001b[39m):\n\u001b[0;32m-> 1496\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mhandle_torch_function\u001b[49m\
u001b[43m(\u001b[49m\u001b[43mrelu\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \
u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\
u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\
u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\
u001b[43minplace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minplace\
u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1497\u001b[0m \u001b[38;5;28;01mif\
u001b[39;00m inplace:\n\u001b[1;32m 1498\u001b[0m result \u001b[38;5;241m=\
u001b[39m torch\u001b[38;5;241m.\u001b[39mrelu_(\u001b[38;5;28minput\u001b[39m)\
n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/overrides.py:1630\
u001b[0m, in \u001b[0;36mhandle_torch_function\u001b[0;34m(public_api,
relevant_args, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1626\u001b[0m \
u001b[38;5;28;01mif\u001b[39;00m _is_torch_function_mode_enabled():\n\u001b[1;32m
1627\u001b[0m \u001b[38;5;66;03m# if we're here, the mode must be set to a
TorchFunctionStackMode\u001b[39;00m\n\u001b[1;32m 1628\u001b[0m \
u001b[38;5;66;03m# this unsets it and calls directly into TorchFunctionStackMode's
torch function\u001b[39;00m\n\u001b[1;32m 1629\u001b[0m \
u001b[38;5;28;01mwith\u001b[39;00m _pop_mode_temporarily() \u001b[38;5;28;01mas\
u001b[39;00m mode:\n\u001b[0;32m-> 1630\u001b[0m result \u001b[38;5;241m=\
u001b[39m \u001b[43mmode\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\
u001b[43m__torch_function__\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpublic_api\
u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtypes\u001b[49m\
u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\
u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\
u001b[1;32m 1631\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m result \
u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \
u001b[38;5;28mNotImplemented\u001b[39m:\n\u001b[1;32m 1632\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m result\n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/utils/_device.py:79\
u001b[0m, in \u001b[0;36mDeviceContext.__torch_function__\u001b[0;34m(self, func,
types, args, kwargs)\u001b[0m\n\u001b[1;32m 77\u001b[0m \u001b[38;5;28;01mif\
u001b[39;00m func \u001b[38;5;129;01min\u001b[39;00m _device_constructors() \
u001b[38;5;129;01mand\u001b[39;00m kwargs\u001b[38;5;241m.\u001b[39mget(\
u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdevice\u001b[39m\u001b[38;5;124m'\
u001b[39m) \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\
n\u001b[1;32m 78\u001b[0m kwargs[\u001b[38;5;124m'\u001b[39m\
u001b[38;5;124mdevice\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\
u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdevice\n\
u001b[0;32m---> 79\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\
u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\
u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\
u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\
u001b[49m\n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/nn/functional.py:1500\
u001b[0m, in \u001b[0;36mrelu\u001b[0;34m(input, inplace)\u001b[0m\n\u001b[1;32m
1498\u001b[0m result \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\
u001b[39mrelu_(\u001b[38;5;28minput\u001b[39m)\n\u001b[1;32m 1499\u001b[0m \
u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1500\u001b[0m result \
u001b[38;5;241m=\u001b[39m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\
u001b[39;49m\u001b[43mrelu\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\
u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1501\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m result\n","File
\u001b[0;32m/opt/conda/lib/python3.10/site-packages/torch/fx/traceback.py:72\
u001b[0m, in \u001b[0;36mformat_stack\u001b[0;34m()\u001b[0m\n\u001b[1;32m 69\
u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m [current_meta\u001b[38;5;241m.\
u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstack_trace\u001b[39m\
u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\
u001b[39m)]\n\u001b[1;32m 70\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\
u001b[1;32m 71\u001b[0m \u001b[38;5;66;03m# fallback to
traceback.format_stack()\u001b[39;00m\n\u001b[0;32m---> 72\u001b[0m \
u001b[38;5;28;01mreturn\u001b[39;00m traceback\u001b[38;5;241m.\
u001b[39mformat_list(\u001b[43mtraceback\u001b[49m\u001b[38;5;241;43m.\
u001b[39;49m\u001b[43mextract_stack\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\
u001b[49m[:\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m])\n","File \
u001b[0;32m/opt/conda/lib/python3.10/traceback.py:227\u001b[0m, in \
u001b[0;36mextract_stack\u001b[0;34m(f, limit)\u001b[0m\n\u001b[1;32m 225\
u001b[0m \u001b[38;5;28;01mif\u001b[39;00m f \u001b[38;5;129;01mis\u001b[39;00m \
u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 226\u001b[0m f \
u001b[38;5;241m=\u001b[39m sys\u001b[38;5;241m.\u001b[39m_getframe()\
u001b[38;5;241m.\u001b[39mf_back\n\u001b[0;32m--> 227\u001b[0m stack \
u001b[38;5;241m=\u001b[39m \u001b[43mStackSummary\u001b[49m\u001b[38;5;241;43m.\
u001b[39;49m\u001b[43mextract\u001b[49m\u001b[43m(\u001b[49m\u001b[43mwalk_stack\
u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m)\u001b[49m\
u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlimit\u001b[49m\
u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlimit\u001b[49m\u001b[43m)\u001b[49m\n\
u001b[1;32m 228\u001b[0m stack\u001b[38;5;241m.\u001b[39mreverse()\n\u001b[1;32m
229\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m stack\n","File \
u001b[0;32m/opt/conda/lib/python3.10/traceback.py:376\u001b[0m, in \
u001b[0;36mStackSummary.extract\u001b[0;34m(klass, frame_gen, limit, lookup_lines,
capture_locals)\u001b[0m\n\u001b[1;32m 374\u001b[0m \u001b[38;5;28;01melse\
u001b[39;00m:\n\u001b[1;32m 375\u001b[0m f_locals \u001b[38;5;241m=\
u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m--> 376\u001b[0m
result\u001b[38;5;241m.\u001b[39mappend(\u001b[43mFrameSummary\u001b[49m\
u001b[43m(\u001b[49m\n\u001b[1;32m 377\u001b[0m \u001b[43m \u001b[49m\
u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\
u001b[43mlineno\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mname\
u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlookup_line\u001b[49m\
u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\
u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mlocals\u001b[39;49m\
u001b[38;5;241;43m=\u001b[39;49m\u001b[43mf_locals\u001b[49m\u001b[43m)\u001b[49m)\
n\u001b[1;32m 378\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m filename \
u001b[38;5;129;01min\u001b[39;00m fnames:\n\u001b[1;32m 379\u001b[0m
linecache\u001b[38;5;241m.\u001b[39mcheckcache(filename)\n","\
u001b[0;31mKeyboardInterrupt\u001b[0m:
"],"ename":"KeyboardInterrupt","evalue":"","output_type":"error"},
{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 0
Axes>"},"metadata":{}}]},{"cell_type":"code","source":"","metadata":
{"id":"2TPoufxnnxCD"},"execution_count":null,"outputs":[]},
{"cell_type":"markdown","source":"{-pOq,r->(sY-t),-s} imp -rYq\n\n* List item\n\
n* List item\n* List item\n\n\n* List item\n\n\n{-( ( (-pOq) Y (r->(sY-t)) Y
(-s) ) -> (-rYq)) }\n{( (-pOq) Y (r->(sY-t)) Y (-s) ) Y -(-rYq) }\n{( (-pOq) Y (r-
>(sY-t)) Y (-s) ) , -(-rYq) }\n{ (-pOq) , (r->(sY-t)) , (-s) , (rO-q) }\n{ (-
pOq) , (-rO(sY-t)) , (-s) , (rO-q) }\n{ (-pOq) , -r , (-s) , (rO-q) } { (-pOq) ,
(sY-t) , (-s) , (rO-q) }\n { (-pOq) , -r , (-s) , r } { (-pOq) , -r , (-s) ,-
q }\n\n\n\n { (-p) , -r , (-s) ,-q } { (-pOq) , s,-t
, (-s) , (rO-q) }\n x\n\
n","metadata":{"id":"4kXPEUA1QyWH"}},{"cell_type":"code","source":"pipeline=1000\
ntrains.deterministic=True\nprint(trains.deterministic)\nfor i in range(pipeline):\
n
trains.train()","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":
1000},"executionInfo":
{"elapsed":77237,"status":"error","timestamp":1728081585552,"user":
{"displayName":"DAVID SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"},"user_tz":300},"id":"BH7a6onBkpZX","output
Id":"f1916970-c3df-434d-ff0d-d71abf109a99","execution":{"iopub.status.busy":"2024-
10-07T19:48:30.111095Z","iopub.status.idle":"2024-10-
07T19:48:30.111669Z","shell.execute_reply.started":"2024-10-
07T19:48:30.111371Z","shell.execute_reply":"2024-10-
07T19:48:30.111402Z"},"trusted":true},"execution_count":null,"outputs":[]},
{"cell_type":"code","source":"#get all asci code\nimport string\n\
nascilist=list(\"abcdefghijkl\")\n\nimage=\"eldiablo.png\"\
nimgtonumpy=skimage.io.imread(image)\n#do a mean between all the channels\
nimgtonumpy=np.mean(imgtonumpy,axis=2)\n#normalize\nimgtonumpy=imgtonumpy/255\
n#resize\nimgtonumpy=skimage.transform.resize(imgtonumpy,(50,100))\
nshape=imgtonumpy.shape\nflatten=np.reshape(imgtonumpy,(-1))\ntoascii=\"\"\nfor i
in range(len(flatten)):\n if i%(shape[1])== 0:\n print(shape[1])\n
toascii+=\"\\n\"\n\n\n toascii+=ascilist[int(flatten[i]*(len(ascilist)-1))]\n\
nprint(toascii)\n","metadata":{"colab":{"base_uri":"https://
localhost:8080/"},"executionInfo":
{"elapsed":216,"status":"ok","timestamp":1727975791655,"user":{"displayName":"DAVID
SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"},"user_tz":300},"id":"SSNg8LVbOL_5","output
Id":"f96c3303-fcf8-477f-f395-8687f1c0ca55","execution":{"iopub.status.busy":"2024-
10-07T19:48:30.113560Z","iopub.status.idle":"2024-10-
07T19:48:30.114129Z","shell.execute_reply.started":"2024-10-
07T19:48:30.113808Z","shell.execute_reply":"2024-10-
07T19:48:30.113836Z"},"trusted":true},"execution_count":null,"outputs":[]},
{"cell_type":"markdown","source":"satisfacible\n\n{-(p->( (-pOq ) ->q ) )}\n{p, -(
(-pOq ) ->q ) )}\n{p, -( -(-pOq ) O q ) )}\n{p, (-pOq ) Y -q }\n{p, (-pOq ) , q
}\n{p, -p,q},{","metadata":{"id":"cTi7xYdIJmTN"}},
{"cell_type":"markdown","source":"{ (-pOq),( q-> ( (-rY-p) Y (pOr) ) ) }\n{ (-
pOq),( -q O ( (-rY-p) Y (pOr) ) ) }","metadata":{"id":"PnA5wtBxLCGk"}},
{"cell_type":"markdown","source":"pY(-qO-p)\n{p,-qO-p}\n{p,-q} {p,-p}\n .
x","metadata":{"id":"RevKTpyY6pND"}},{"cell_type":"markdown","source":"(pOq)Y(-pO-
q)\n{pOq,-pO-q}\n{p,-pO-q} {q,-pO-q}\n{p,-p} {p,-q} {q,-p} {q,-q}\n x o
o x\n","metadata":{"id":"GTuG2ueN68nE"}},
{"cell_type":"markdown","source":"{pOq,-pY-q}\n{p,-pY-q} {q,-pY-q}\n{p,-p,-q} {q,-
p,-q}\n x x\n","metadata":{"id":"p7ltRXV27yoz"}},
{"cell_type":"markdown","source":"{p->q,q->p}\n{p","metadata":{"id":"K2zKeEwI-
bhl"}},{"cell_type":"code","source":"#test layernorm on vector\
nvector=torch.Tensor([1,2,3])\nvector=torch.reshape(vector,(1,1,-1))\
nlayernorm=torch.nn.LayerNorm((1,3))\nresult=layernorm(vector)\
nprint(result)","metadata":{"colab":{"base_uri":"https://
localhost:8080/"},"executionInfo":
{"elapsed":208,"status":"ok","timestamp":1727536071355,"user":{"displayName":"DAVID
SANTIAGO SANCHEZ
CEPEDA","userId":"09385389865282990454"},"user_tz":300},"id":"QY9Q6seSHajs","output
Id":"757a01df-4ea6-4aa8-aa02-b4a27c2e6738","execution":{"iopub.status.busy":"2024-
10-07T19:48:30.115554Z","iopub.status.idle":"2024-10-
07T19:48:30.116376Z","shell.execute_reply.started":"2024-10-
07T19:48:30.116077Z","shell.execute_reply":"2024-10-
07T19:48:30.116115Z"},"trusted":true},"execution_count":null,"outputs":[]},
{"cell_type":"markdown","source":"\n","metadata":{"id":"RbykQvuOHbE0"}}]}