Hugging Face's logo

ElmanGhazaei
/
CSSM

Model card Files
xet
Community
CSSM
File size: 14,627 Bytes 
b59f460
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
 
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from Mamba import Mamba\n",
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = torch.rand(size = (1,5,16))\n",
    "\n",
    "num_layers = 5\n",
    "d_model = 16\n",
    "d_state = 16\n",
    "d_conv = 4\n",
    "\n",
    "mamba = Mamba(num_layers=num_layers,d_model=d_model, d_conv=d_conv, d_state=d_state)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 5, 32, 16])\n",
      "torch.Size([1, 5, 32, 16])\n",
      "torch.Size([1, 5, 32, 16])\n",
      "torch.Size([1, 5, 32, 16])\n",
      "torch.Size([1, 5, 32, 16])\n"
     ]
    }
   ],
   "source": [
    "y1,y2 = mamba(x,x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([1, 5, 16])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y2.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "include_paths() got an unexpected keyword argument 'cuda'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[7], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mxlstm\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[1;32m      2\u001b[0m     xLSTMBlockStack,\n\u001b[1;32m      3\u001b[0m     xLSTMBlockStackConfig,\n\u001b[1;32m      4\u001b[0m     mLSTMBlockConfig,\n\u001b[1;32m      5\u001b[0m     mLSTMLayerConfig,\n\u001b[1;32m      6\u001b[0m     sLSTMBlockConfig,\n\u001b[1;32m      7\u001b[0m     sLSTMLayerConfig,\n\u001b[1;32m      8\u001b[0m     FeedForwardConfig,\n\u001b[1;32m      9\u001b[0m )\n\u001b[1;32m     11\u001b[0m cfg \u001b[38;5;241m=\u001b[39m xLSTMBlockStackConfig(\n\u001b[1;32m     12\u001b[0m     mlstm_block\u001b[38;5;241m=\u001b[39mmLSTMBlockConfig(\n\u001b[1;32m     13\u001b[0m         mlstm\u001b[38;5;241m=\u001b[39mmLSTMLayerConfig(\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     30\u001b[0m \n\u001b[1;32m     31\u001b[0m )\n\u001b[1;32m     33\u001b[0m xlstm_stack \u001b[38;5;241m=\u001b[39m xLSTMBlockStack(cfg)\n",
      "File \u001b[0;32m~/anaconda3/envs/CDDD/lib/python3.13/site-packages/xlstm/__init__.py:3\u001b[0m\n\u001b[1;32m      1\u001b[0m __version__ \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m2.0.2\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mblocks\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmlstm\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mblock\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m mLSTMBlock, mLSTMBlockConfig\n\u001b[1;32m      4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mblocks\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmlstm\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlayer\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m mLSTMLayer, mLSTMLayerConfig\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mblocks\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mslstm\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mblock\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m sLSTMBlock, sLSTMBlockConfig\n",
      "File \u001b[0;32m~/anaconda3/envs/CDDD/lib/python3.13/site-packages/xlstm/blocks/mlstm/block.py:5\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# Copyright (c) NXAI GmbH and its affiliates 2024\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;66;03m# Maximilian Beck\u001b[39;00m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mdataclasses\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m dataclass, field\n\u001b[0;32m----> 5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mxlstm_block\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m xLSTMBlock, xLSTMBlockConfig\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlayer\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m mLSTMLayerConfig\n\u001b[1;32m      9\u001b[0m \u001b[38;5;129m@dataclass\u001b[39m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mclass\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mmLSTMBlockConfig\u001b[39;00m:\n",
      "File \u001b[0;32m~/anaconda3/envs/CDDD/lib/python3.13/site-packages/xlstm/blocks/xlstm_block.py:12\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcomponents\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mln\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m LayerNorm\n\u001b[1;32m     11\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmlstm\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlayer\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m mLSTMLayer, mLSTMLayerConfig\n\u001b[0;32m---> 12\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mslstm\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mlayer\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m sLSTMLayer, sLSTMLayerConfig\n\u001b[1;32m     16\u001b[0m \u001b[38;5;129m@dataclass\u001b[39m\n\u001b[1;32m     17\u001b[0m \u001b[38;5;28;01mclass\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mxLSTMBlockConfig\u001b[39;00m:\n\u001b[1;32m     18\u001b[0m     mlstm: Optional[mLSTMLayerConfig] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[0;32m~/anaconda3/envs/CDDD/lib/python3.13/site-packages/xlstm/blocks/slstm/layer.py:15\u001b[0m\n\u001b[1;32m     12\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcomponents\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01minit\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m small_init_init_\n\u001b[1;32m     14\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mtorch\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m nn\n\u001b[0;32m---> 15\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcell\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m sLSTMCell, sLSTMCellConfig\n\u001b[1;32m     18\u001b[0m \u001b[38;5;129m@dataclass\u001b[39m\n\u001b[1;32m     19\u001b[0m \u001b[38;5;28;01mclass\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01msLSTMLayerConfig\u001b[39;00m(sLSTMCellConfig):\n\u001b[1;32m     20\u001b[0m     embedding_dim: \u001b[38;5;28mint\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m\n",
      "File \u001b[0;32m~/anaconda3/envs/CDDD/lib/python3.13/site-packages/xlstm/blocks/slstm/cell.py:12\u001b[0m\n\u001b[1;32m      9\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mtorch\u001b[39;00m\n\u001b[1;32m     11\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mtorch\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mautograd\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfunction\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m once_differentiable\n\u001b[0;32m---> 12\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msrc\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcuda_init\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m load\n\u001b[1;32m     13\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msrc\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mvanilla\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[1;32m     14\u001b[0m     slstm_forward,\n\u001b[1;32m     15\u001b[0m     slstm_forward_step,\n\u001b[1;32m     16\u001b[0m     slstm_pointwise_function_registry,\n\u001b[1;32m     17\u001b[0m )\n\u001b[1;32m     18\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcomponents\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutil\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m conditional_decorator, round_to_multiple, ParameterProxy\n",
      "File \u001b[0;32m~/anaconda3/envs/CDDD/lib/python3.13/site-packages/xlstm/blocks/slstm/src/cuda_init.py:30\u001b[0m\n\u001b[1;32m     27\u001b[0m curdir \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mdirname(\u001b[38;5;18m__file__\u001b[39m)\n\u001b[1;32m     29\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mcuda\u001b[38;5;241m.\u001b[39mis_available():\n\u001b[0;32m---> 30\u001b[0m     os\u001b[38;5;241m.\u001b[39menviron[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCUDA_LIB\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39msplit(\u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mutils\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcpp_extension\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minclude_paths\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcuda\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m])[\u001b[38;5;241m0\u001b[39m], \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlib\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     33\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mload\u001b[39m(\u001b[38;5;241m*\u001b[39m, name, sources, extra_cflags\u001b[38;5;241m=\u001b[39m(), extra_cuda_cflags\u001b[38;5;241m=\u001b[39m(), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m     34\u001b[0m     suffix \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
      "\u001b[0;31mTypeError\u001b[0m: include_paths() got an unexpected keyword argument 'cuda'"
     ]
    }
   ],
   "source": [
    "from xlstm import (\n",
    "    xLSTMBlockStack,\n",
    "    xLSTMBlockStackConfig,\n",
    "    mLSTMBlockConfig,\n",
    "    mLSTMLayerConfig,\n",
    "    sLSTMBlockConfig,\n",
    "    sLSTMLayerConfig,\n",
    "    FeedForwardConfig,\n",
    ")\n",
    "\n",
    "cfg = xLSTMBlockStackConfig(\n",
    "    mlstm_block=mLSTMBlockConfig(\n",
    "        mlstm=mLSTMLayerConfig(\n",
    "            conv1d_kernel_size=4, qkv_proj_blocksize=4, num_heads=4\n",
    "        )\n",
    "    ),\n",
    "    slstm_block=sLSTMBlockConfig(\n",
    "        slstm=sLSTMLayerConfig(\n",
    "            # backend=,\n",
    "            num_heads=4,\n",
    "            conv1d_kernel_size=4,\n",
    "            bias_init=\"powerlaw_blockdependent\",\n",
    "        ),\n",
    "        feedforward=FeedForwardConfig(proj_factor=1.3, act_fn=\"gelu\"),\n",
    "    ),\n",
    "    context_length=256,\n",
    "    num_blocks=7,\n",
    "    embedding_dim=128,\n",
    "    slstm_at=[1],\n",
    "\n",
    ")\n",
    "\n",
    "xlstm_stack = xLSTMBlockStack(cfg)\n",
    "\n",
    "x = torch.randn(4, 256, 128).to(torch.device(\"cuda\"))\n",
    "xlstm_stack = xlstm_stack.to(torch.device(\"cuda\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os \n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "t = os.path.join(\"/media/elman/backup/DG_CD/WHU-CD-256/list/train.txt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "f = np.array((pd.read_csv(t,names=[\"ttt\"])))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'whucd_00267.png'"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f[1].item()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "CDDD",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}